Exact SEC Metric Recall

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

Beyond the readOnlyHint annotation, the description discloses that results are server-side verified, include provenance, and that missing data triggers SAFE_REFUSAL rather than fabrication. This adds meaningful behavioral context about verification and failure modes beyond what annotations provide.

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?

Three short, punchy sentences pack a complete picture. Every clause earns its place: exactness, scope, verification, provenance, failure behavior, and an anti-pattern all communicated without filler.

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 lookup tool with a clear input contract and output schema, the description fully captures what matters: what it does, how it ensures accuracy, how it fails safely, and what it refuses to do. No important context is missing for an agent to invoke it correctly.

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%, so the baseline of 3 applies. The description reinforces the company+metric+period trio in its purpose statement, which maps naturally to the three required parameters, but the schema already documents them fully. It adds no format or domain constraints beyond what's present.

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?

"Exact EDGAR metric recall for company+metric+period" uses a specific verb (recall), resource (EDGAR metric), and scope, clearly distinguishing it from siblings like query_financial_sec and compute_sec_cagr. The word "Exact" and the closing "No LLM math" further position it as a precise, factual lookup tool.

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?

Explicitly states when this tool is appropriate (exact factual recall) and what to do instead when data is missing ("SAFE_REFUSAL when missing"). "No LLM math" implicitly excludes it for computation tasks, pointing users toward math-capable siblings like compute_sec_cagr.

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