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

Beyond the annotations (readOnly, idempotent, etc.), the description adds specific behavioral details: for companies it pulls latest 10-K data with correct off-calendar fiscal year handling, for drugs it pulls FAERS/FDA/trial counts, results are sorted by primary metric, and it returns 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 a single dense paragraph of about 80 words with no fluff. It front-loads the most common usage patterns and immediately states the core purpose. Every sentence adds essential information about triggers, alternatives, data sources, or sorting behavior.

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, sorting, citation URIs) and the absence of an output schema, the description covers all necessary information for an agent to correctly invoke the tool and interpret results. It replaces the need for multiple sequential lookups and explains what each entity type returns.

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 descriptions for both parameters. The description adds value by providing concrete examples (e.g., 'AAPL','MSFT' for company values, 'ozempic','mounjaro' for drug values), explaining the behavior of the type parameter (what data each pulls), and reiterating constraints (min 2, max 5 items). This goes beyond the schema's simple type/enum descriptions.

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 starts with multiple natural language triggers, clearly states it performs side-by-side comparisons of 2-5 companies or drugs in a single parallel call, and distinguishes from siblings like 'entity_profile' (single entity) and 'validate_claim' (validation vs comparison). It also specifies the data sources for each entity type.

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 'ALWAYS PREFER over sequential single-pack lookups' and notes it replaces 8-15 sequential lookups. It provides strong positive guidance on when to use, but lacks explicit when-not or alternative tools, though sibling tools are listed in context.

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