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

The annotation already declares readOnlyHint=true, so the agent knows this is a safe read operation. The description adds valuably beyond that by revealing 'Server-side verified fact with provenance' (meaning results are authoritative and cite sources) and 'SAFE_REFUSAL when missing' (meaning the tool will explicitly decline rather than hallucinate), which is critical behavioral context for a retrieval tool. It also states 'No LLM math,' warning against the tool being used for computation. The only gap is not explaining the format or pagination of the response, but the output schema likely covers that.

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 description is a single sentence plus two short phrases: 'Exact EDGAR metric recall for company+metric+period. Server-side verified fact with provenance; SAFE_REFUSAL when missing. No LLM math.' Every part earns its place—purpose, data source/quality, error handling, and behavioral constraint. It is front-loaded and dense with useful information.

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?

Given the tool's complexity (4 parameters, 3 required), the presence of an output schema to explain return values, and the annotation readOnlyHint=true, the description is complete. It covers the core purpose, the data's verified nature, refusal behavior, and a key limitation (no math). There are no apparent gaps for an agent to make a mistake in invoking this tool.

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?

The input schema has 100% description coverage, with clear descriptions for all four parameters. The description does not add additional meaning beyond the schema descriptions themselves, but it does tie them together contextually by stating the inputs are 'company+metric+period' and noting the optional 'low_tokens' parameter (though not explicitly named). Since schema coverage is complete, a baseline score of 3 is appropriate.

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?

The description clearly states the tool's purpose: 'Exact EDGAR metric recall for company+metric+period.' It specifies a verb ('recall'), a resource ('EDGAR metric'), and the required inputs (company, metric, period). This distinguishes it from siblings like 'compute_sec_cagr' (which uses arithmetic) and 'query_sec_sector_peers' (which targets peers).

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 description explicitly notes 'Server-side verified fact with provenance; SAFE_REFUSAL when missing. No LLM math.' This tells the agent when the tool will return a verifiable result versus refuse (SAFE_REFUSAL), and that it should not be used for mathematical derivations or guessing. It lacks explicit guidance on when to prefer alternatives like 'compute_sec_cagr' for growth rates or 'query_financial_sec' for broader searches, but the sibling names and the 'No LLM math' hint provide adequate contextual clues.

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