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

Annotations already declare readOnlyHint=true, so the description need not repeat safety. It adds meaningful behavioral context: each kind's output semantics (e.g., red_flags returns status and dated evidence, event_text returns 'the most recent filed events'), and the date-window behavior via start/end. This goes beyond the annotation without contradicting it.

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 structured as a bullet list that front-loads the core purpose and then details each kind. Every sentence adds value—no filler—and the alternatives are stated at the end. It is longer than average but justified by the many kind variants, and remains scannable.

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 tool with no output schema and many kind variants, the description covers all necessary call parameters and return semantics (e.g., status and dated evidence for red_flags). It also addresses windowing and alternatives. It doesn't detail the exact JSON shape, but that is not critical for selection; the description is complete enough 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%, so the description carries the full burden for parameters. It thoroughly explains the kind enum with aliases and meanings, defines start/end as ISO date bounds, and notes that omitting them returns the most recent limit results. It does not explicitly explain entity, but that is a common identifier likely understood from context; overall, it compensates well for the missing schema descriptions.

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 states a specific purpose: retrieving a company's disclosures and coverage, with a clear enumeration of the kinds (events, press_releases, news, event_text, red_flags) and what each returns. It distinguishes itself from siblings by explicitly naming search_filings and get_filing_text as alternatives for different tasks, so an agent can tell them apart without opening schemas.

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 provides explicit when-to-use guidance by enumerating each kind and their aliases, and directly states the conditions for alternatives: 'To query across filings use search_filings; to read a specific 10-K/10-Q section use get_filing_text.' This removes ambiguity about when to pick this tool over its siblings.

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