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

Annotations indicate read-only, idempotent, non-destructive behavior. The description adds valuable context beyond annotations: it discloses data sources (SEC EDGAR/XBRL, FAERS), handling of off-calendar fiscal years, sorting by primary metric, and inclusion of citation URIs. No contradictions.

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 compact yet informative, front-loading the core purpose with examples. It contains about 5 sentences, each adding value. Some redundancy (e.g., repeating 'side-by-side comparison' and 'head to head') but overall efficient. Minor room for tightening.

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 moderate complexity (two entity types, multiple data sources, no output schema), the description covers key aspects: what data is returned per type, sorting behavior, and citation URIs. It also explains edge cases like off-calendar fiscal years. The absence of an output schema is mitigated by mentioning 'paired data + citation URIs'. Sufficient for confident invocation.

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% with clear parameter descriptions, so baseline is 3. The description adds significant meaning: for 'type', it specifies what data is pulled for company (revenue, net income, cash, debt) and drug (adverse events, FDA approvals, trials). For 'values', it explains tickers/CIKs vs. drug names. This extra context helps the agent understand the semantics beyond the enum and array constraints.

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 clearly states the tool does side-by-side comparison of 2-5 companies or drugs, with specific verb-resource pairs like 'compare entities'. It distinguishes from siblings such as entity_profile by saying it replaces sequential lookups and is preferred over single-pack lookups.

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 guidance is provided: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It gives natural language examples for when to use (e.g., 'which is bigger/better', 'rank these companies') and implies not to use for single entity lookups.

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