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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond that: the put_call/direction warning (never report a put as a holding), the notional-vs-premium caveat for options, the whole-USD vs thousands change for pre-2023 filings, and the instruction to rank by pct_of_long_equity and read position_summary/interpretation_note. This is exactly the kind of non-obvious behavior an agent needs.

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 dense but every sentence earns its place: scope, examples, use cases, caveats, and ranking instructions. It is front-loaded with the core purpose and the manager-vs-stock distinction. It is longer than average, but the complexity of 13F data justifies the length; the put_call warning alone prevents a serious reporting error.

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 read-only lookup tool with no output schema, the description covers everything an agent needs to call it correctly and interpret results: input format, examples, scope limitations, value units, option semantics, and ranking guidance. The only minor gap is that it doesn't describe the exact JSON shape of the response, but the description's mention of fields (value, shares, pct_of_long_equity, position_summary, interpretation_note) compensates.

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%, so the schema already documents all four parameters. The description adds value by clarifying that ticker_or_cik (and its aliases) refers to the manager, not the held stock, and by giving concrete CIK examples. It also explains the meaning of the returned value field (whole USD vs thousands), which is not in the schema. It doesn't add much about `limit`, but the schema already covers that.

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 statement: it returns the authoritative 13F-HR portfolio of an institutional manager, with share counts, position values, and report period. It explicitly distinguishes the manager (the filer) from the held stock, and gives concrete examples (BRK-B, Bridgewater CIK). This clearly differentiates it from siblings like edgar_fund_holdings and edgar_company_facts.

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 gives explicit when-to-use examples ('what does Berkshire own', 'Bridgewater's biggest positions', 'which funds hold $TICKER') and states the key input requirement: pass the MANAGER's ticker or CIK, not the held stock. It also notes the run-per-manager behavior and the 13F scope (US-listed long equity, >$100M AUM, ~45-day lag), which helps an agent decide when this tool is appropriate versus alternatives.

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