Calibration Ledger — trust a forecast, with evidence (beta)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing that each call starts a run of the Apify Actor 'publicrecords/calibration-ledger' through mcp.apify.com using the caller's own APIFY_TOKEN and Apify account (a real cost/quota implication). It confirms the operation only reads public web data and mutates nothing on the source site, and explains the return shape plus run/dataset IDs for paging — none of which the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence restates the title verbatim, and the 'When to use' and 'Returns' paragraphs repeat the error distribution/bias/worst misses list already given in the first paragraph. The auth/Apify and read-only sentences earn their place, but the definition is roughly twice the length it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, seven-mode tool with no output schema, the description covers what is returned (dataset rows as structured JSON, plus run/dataset IDs for paging), the auth requirement, the billing/free distinction, and the organizations-only scope. Weakness is mode selection: the seven modes and their required fields are only implicit, so an agent must read the schema carefully to know which fields each mode needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the mode enum itself documents text vs lookup/score/compare, so the description adds no parameter-level meaning beyond a restatement of the text-mode example. Baseline 3 is appropriate when the schema already carries all twelve parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: given a claim from a named institution, it returns that organization's track record (error distribution, intervals, bias, band coverage, worst misses with source links). The scope boundary 'Organizations only, never people' and the concrete source list (IMF, OECD, Fed/FOMC, SPF, ECB SPF, listed issuer) make the resource unambiguous; no sibling tool overlaps this function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'When to use' block gives an explicit trigger: someone cites an institutional forecast and you need to know how accurate that institution has been. It also states a when-not (people are out of scope) and that 'no coverage' is an acceptable honest answer. It does not route between the seven modes, but that guidance lives in the schema's mode description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.