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

Annotations already declare it as a safe, idempotent, open-world read, so the safety profile is covered. The description adds genuinely useful context beyond that: it conservatively returns evidence plus deterministic stance signals, and it warns that a filing establishes what the company reported, not real-world truth — an important epistemic caveat for interpretation.

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 tight sentences, front-loaded with the verdict scope, followed by the return shape and the interpretive caveat. Every sentence earns its place with no redundancy.

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?

With no output schema, the description usefully previews the return (evidence plus stance signals) and the verdict range. The main gap is parameter-level guidance for the optional filters and numeric caps, which an 8-param tool would benefit from.

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 coverage is only 63%, and limit, filings, and history carry no descriptions at all in the schema. The description mentions no parameters whatsoever, so it does not compensate for the undocumented third — defaults, the filings/limit caps, and the history flag remain unexplained.

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 (assess/verify) and resource (a claim against SEC filing evidence) and enumerates the verdict spectrum, which makes it clearly distinct from retrieval siblings like search_evidence. It never names a sibling explicitly, so it falls just short of the 5 benchmark that requires explicit differentiation.

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?

Usage is implied: you supply a claim and an issuer to get a verdict. But there is no explicit when-to-use guidance, no statement of when to prefer search_evidence or build_evidence_pack, and no prerequisites (e.g., whether the issuer must first be resolved via resolve_issuer).

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