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

Goes well beyond readOnly/idempotent annotations: 45-day filing lag, long-only US equity and option scope, absence of shorts/cash/bonds/non-US, cohort being a chosen list rather than a census, delayed derived data, and a mandatory dated citation on both success and failure. A no-filing quarter returning an answer rather than an error is exactly the kind of behavior an agent cannot infer from annotations.

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 relevant content (trigger, returns, coverage, exclusions, limits) is well front-loaded, but a large trailing block is boilerplate copied from a market-level tool: 'a wall, a flip, a regime or a settlement', 'never present a level, wall or regime without its timestamp', plus a repeated citation rule. None of that earns its place in a 13F receipt tool and it dilutes the operative guidance.

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?

Covers scope, cohort limits, data lag, failure behavior, and citation obligations; an output schema exists so return-shape explanation is optional rather than required. What is missing is anything about ordering, pagination, or truncation when limit caps holdings rows — though 'largest reported value first' in the schema partially covers ordering.

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 100% and the schema already documents limit (1-50, largest value first), manager slug semantics including the 'outside the cohort returns the cohort' fallback, and YYYY-qN quarter format. The description only restates 'omit the manager to list the published cohort', adding little beyond the schema, so baseline 3 applies.

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 ('returns the reported positions... accession number, period of report, acceptance date, revision history') and a precise trigger ('what an institutional manager reported holding in a quarter'). It also differentiates itself from the nearest sibling by name ('congressional filings (get_congressional_disclosures)' and the real-time/performance tools it is not).

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?

Explicit 'Use this when...' plus an explicit 'Not for:' exclusion list (current holdings, price, performance, returns, rankings, congressional filings) with the alternative named. The empty-quarter case is clarified as a valid answer rather than an error, which removes a common misroute.

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