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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: quarter coverage from 2024-12-31, daily loading before the 45-day deadline, the `coverage.status: not_yet_filed` fallback with a `coverage_caveat` naming the older quarter, and the explicit statement that no email exists and none should be inferred. However it does not describe result size, ordering guarantees beyond 'ranked by value', or pagination behavior for the 1-200 limit.

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 most important information (what it is, how to look it up, what it excludes) is front-loaded in the first three sentences. The remainder is dense but mostly earns its place through coverage and caveat details; there is mild redundancy with the schema on manager matching and the issuer alias note.

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?

This is a complex, multi-mode lookup with a nested issuer object and no output schema, so the description must carry return-value semantics — and it does: positions by value, share-change flags, contact/signatory block citable to an accession number, and the coverage status enum. Nothing an agent needs in order to call it correctly and interpret the result is missing.

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 is 3. The description restates what the schema already documents — manager partial matching and 'the largest matching filer wins' are both in the `manager` and `cik` field descriptions — and adds little new syntax or format guidance, though the rationale for name ambiguity is a helpful gloss on why CIK is preferred.

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 opens with a precise verb-and-resource statement ('an institutional manager's reported equity book from SEC Form 13F — top positions by value, with quarter-over-quarter share changes and new/increased/decreased flags') and explicitly names what the tool is NOT ('this tool identifies the FILING MANAGER, not the issuer held — for who owns a stock, use holdings_by_security'). An agent can distinguish it from holdings_by_security without opening either schema.

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?

It gives concrete example questions that select this tool, spells out the two lookup modes (manager partial match vs exact CIK) and which to prefer, and routes the ownership-by-stock question to the sibling tool. It also states scope exclusions ('no shorts, cash, bonds or non-US listings') and the lag, so an agent knows when the answer is inappropriate.

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