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

The annotations (readOnlyHint, idempotentHint, etc.) indicate safe, non-destructive behavior. The description adds rich behavioral context: for company type, it pulls real financial data from SEC EDGAR/XBRL with correct handling of off-calendar fiscal years; for drug type, it pulls adverse-event and approval counts. It also mentions sorting by primary metric and returning citation URIs. No contradictions with 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 description is concise (around 100 words) and front-loads the core purpose with query examples. It is structured with clear separation of company vs drug behavior and ends with a summary of benefits. Some redundancy exists ('ALWAYS PREFER' is emphasized), but overall every sentence contributes meaning without excessive verbosity.

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?

Given the tool's complexity (two entity types, multiple data sources) and no output schema, the description covers key behavioral aspects: data origin, financial metrics, drug metrics, sorting, and citation URIs. It also mentions edge-case handling (off-calendar fiscal years). It does not explain error cases or rate limits, but annotations cover idempotency and read-only nature. Overall well-rounded.

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?

With 100% schema description coverage, baseline is 3. The description adds significant meaning beyond the schema: it explains that 'values' should be tickers/CIKs for company type and drug names for drug type, and it specifies the allowed count range (2-5). It also clarifies the effect of the 'type' parameter on data sources and output. This adds value beyond the bare schema.

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 uses specific verbs like 'Compare', 'rank', and 'head to head' and clearly states it produces side-by-side comparisons of 2-5 companies or drugs. It distinguishes from siblings by explicitly noting it replaces 8-15 sequential lookups and should be preferred over single-pack lookups. The examples of natural language queries further clarify the tool's purpose.

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 explicitly says when to use this tool (for comparisons of multiple entities) and strongly urges preference over sequential single-pack lookups. It provides example query patterns. However, it does not explicitly state when NOT to use it (e.g., for single entity queries), though the sibling tool 'entity_profile' exists. Still, the guidance is clear and actionable.

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