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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial operational context: fetch mode latency ('tens of milliseconds') versus slower cross-company calls, the `quality_caveat` response marker, default fund/proxy form suppression, and the requirement of an issuer identifier in fetch mode. It also discloses a real behavioral quirk — the rerank profiles are deprecated aliases whose cross-encoder was removed.

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?

Front-loaded with purpose and the two-mode distinction, and most sentences carry routing or constraint information. It is long and dense for a tool description, and the cross_company/quality_caveat behavior is explained twice (description and `scope` schema), which is mild redundancy rather than waste.

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 16-parameter tool with nested objects, enums, and an output schema, the description covers everything an agent needs: mode selection, issuer requirement, non-US routing, coverage limits, and when to expect degraded (caveated) results. Return-value detail is correctly delegated to the output schema.

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 88%, so the baseline is 3, but the description adds genuine semantics beyond the schema: omitting `query` is what triggers fetch mode, `issuer.company_name` is the required route for non-US issuers with no US ticker, and cross-company calls carry a caveat. Minor parameters (limit, fields, exclude_form_type) get no narrative treatment, keeping it just short of a 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?

Opens with a specific verb+resource and scope ('Search SEC filings (10-K, 10-Q, 8-K, registration statements/prospectuses and press exhibits; S&P 500 coverage, ~10 years)'), then immediately splits the tool into two named modes. Coverage boundaries (US SEC plus Sweden/Japan/Korea) are stated, which distinguishes it from siblings like transcript_search and regulation_search without opening any 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 states when to use each mode: 'Use fetch when you already know WHICH document you want and only need its text' versus search mode passing `query`. It also names the alternative scope and when NOT to use it — 'Use scope=cross_company deliberately only for questions that are genuinely about many companies' — and warns to check for `quality_caveat` on those calls.

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