explain_absence
Ask why a factor is NOT in the corpus. The reasoned counterpart to coverage: where a country reports zero rows for an inventory family, this says whether that is the world's limit or our backlog. Five classifications: "structural" (no publisher issues this anywhere — stop looking, and do not sile...
This record as markdown: /tools/com-greencalculus-api/explain-absence.md
What explain_absence does on Api
AI agents call explain_absence to retrieve information from Api without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
family | string | — | Inventory family, e.g. "water", "wtt", "travel", "spend", "heat". |
country | string | — | ISO-3166 alpha-3 code, e.g. "can". |
classification | string | — | Filter: structural | not_yet_sourced | refused | held_not_counted | coupled. |
Parameters from the server's own tool schema.
Why explain_absence is rated Low
Even though explain_absence only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs explain_absence safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Api, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For explain_absence, this is the rule to start with:
explain_absence is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Api, apply this rule, and every explain_absence call is checked against it from then on.
Questions about explain_absence
Ask why a factor is NOT in the corpus. The reasoned counterpart to coverage: where a country reports zero rows for an inventory family, this says whether that is the world's limit or our backlog. Five classifications: "structural" (no publisher issues this anywhere — stop looking, and do not silently substitute another country), "not_yet_sourced" (a publisher exists and is named; it is our backlog), "refused" (we found it and declined — the reason is stated), "held_not_counted" (we DO hold it — see we_hold for the key), "coupled" (empty only because another family is empty). Each record names the publisher checked, the route tried, a confidence and a review date, and reports stale:true once past review. These are authored judgements about what the world publishes, not values derived from our data. Call this before concluding that a gap is permanent, and before telling a user to look elsewhere. It is categorised as a Read tool in the Api MCP Server, which means it retrieves data without modifying state.
explain_absence accepts 3 parameters: family, country, classification. The full parameter table on this page comes from the server's own tool schema.
Register the Api MCP server in PolicyLayer and add a rule for explain_absence: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Api. Nothing to install.
explain_absence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the explain_absence rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for explain_absence. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
explain_absence is provided by the Api MCP server (https://mcp.greencalculus.com). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Api, and thousands of servers like it.
This server
Across the catalogue