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

Annotations already cover read-only/open-world safety, and the description adds real behavioral context beyond them: a credit cost model (1 credit/record, minimum 2) tied to page_size, and the caveat that issuer-name matching is best-effort with no authoritative CUSIP-to-CIK mapping. It does not cover auth or rate-limit specifics, keeping it short of a 5.

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?

Four tight sentences, front-loaded with the core action, then filters, then cost, then the sibling pointer. No filler; every sentence carries distinct information.

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?

An output schema exists, so return values need no explanation. The description covers action, filter semantics, cost implications, and the counting alternative — everything needed to call a 6-parameter search correctly.

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 baseline is 3; the description earns an extra point by tying page_size to a concrete credit cost and contrasting the reliable manager_cik filter against the best-effort issuer_name/cusip filters. It largely mirrors the schema's own wording, so it is not a full 5.

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+resource ('Search institutional investment managers' quarterly 13F portfolio holdings and return the matching positions'), and the two filtering modes (by manager_cik vs by issuer_name/cusip) distinguish it from the counting sibling. An agent can tell exactly what this returns without opening the 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?

Explicitly routes usage: manager_cik for 'a manager's full portfolio', issuer_name/cusip for 'who holds an issuer', and names datasets_sec_institutional_positions_facets as the pre-paging count alternative. Both the when and the alternative are spelled out.

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