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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely non-obvious traits: per-source size ceilings (4 MiB money-market, 1 MiB otherwise), a warning that source JSON is untrusted, that packets may be partial, and that no verification is performed. Those caveats materially affect how an agent should trust and handle the output.

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?

Four short, front-loaded sentences with no filler; the usage condition leads and the constraints follow. Slightly telegraphic phrasing ('No Evidence Carrier verification is performed') costs a little clarity but nothing is wasted.

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 and only one parameter, the description covers what an agent most needs: scope, size limits, trust status of returned JSON, and the possibility of partial packets. The undefined 'Evidence Carrier' term is the one piece of unexplained context.

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 0% and the description never explains the single 'topics' parameter — its enum values, the 1–5 cardinality, or whether topics combine. The only hint is the passing reference to the 'money-market atlas'. The enum strings are self-explanatory, but the description does not compensate for the coverage gap as required at <50%.

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 and resource: 'Retrieve original public documents' — an agent knows this returns source documents rather than computed tables or reviews. It does not, however, name or distinguish itself from any of the eight sibling financial_evidence_* tools, so the differentiation is left to inference.

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?

'only when table detail is insufficient' gives an explicit when-to-use condition and implicitly excludes the common case where tabular results suffice (the query/dataset siblings). The alternative tool is described generically rather than named, which is a minor gap.

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