documents

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds that the output is links to external documents rather than the documents themselves, which is useful context. It does not say what happens with kind=all (how many per category), how limit interacts with categories, or whether recent-only results are returned.

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?

Two compact sentences: one for the resource, one for the kind enumeration. Front-loaded and waste-free, though the enum sentence is dense and 'concall' is unexpanded jargon that a non-finance agent may not parse.

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?

There is no output schema, and the description only hints at return values ('links to...'), without saying whether items include titles, dates, or URLs grouped by category. With 0% schema description coverage on three parameters, an agent must guess at symbol format and limit semantics. Adequate to identify the tool, but thin for correct invocation.

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 schema has no enum on `kind`, so the description carries real weight by enumerating the allowed kind values (all, announcements, annual_reports, credit_ratings, concalls) – that information exists nowhere else. However, `symbol` format and the meaning/behavior of `limit` (default 20, max? pagination?) are left entirely undocumented.

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 concrete resource: links to exchange announcements, annual reports, credit ratings and concall transcripts/presentations/recordings. This is clearly distinct from the sibling tools, which are numeric/analytical (financial_statement, earnings_trend, peers), so an agent can tell this is the document-link lookup tool. It stops short of a full verb phrase like 'Fetch links for a given company symbol', hence 4 not 5.

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 list of document categories implies when the tool is useful (when the user wants filings, ratings or call material rather than numbers), but there is no explicit 'use this when...' statement and no mention of any alternative tool. Usage is inferable but not guided.

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