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

Annotations already declare read-only, idempotent, and non-destructive. The description adds substantive behavioral context: what data is fetched per type (10-K metrics, FAERS counts), how fiscal year offsets are handled, sorting by primary metric, and the return format with citation URIs. This goes well beyond the structured annotation fields.

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 appropriately sized given the tool's complexity, with all sentences contributing to operational clarity. It front-loads the trigger patterns and the core preference rule. The list of example phrases ('which is bigger / better / larger...') is slightly repetitive but helps NLU matching.

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?

The tool has only two parameters and a clear output concept (paired data + URIs), and the description covers the input format, data source nuance, sorting behavior, and return expectations. No output schema exists, so this description fully compensates, making the tool self-contained for an agent to invoke 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?

All parameters are fully described in the schema, so baseline is 3. The description enriches the meaning of both parameters by detailing what each type value returns ('type="company" pulls LATEST 10-K...', 'type="drug" pulls FAERS...') and what the values array should contain (tickers/CIKs vs. drug names). This added context gives the agent a deeper understanding beyond the schema's property 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 opens with concrete natural-language examples ('Compare X and Y', 'X vs Y', 'rank these companies'), then states the core function: side-by-side comparison of 2–5 entities in one parallel call. It clearly distinguishes itself from sibling single-entity tools by explicitly saying 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' The specific verb is 'compare' with a defined resource scope.

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 directs when to use this tool: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', providing direct guidance versus alternatives. It also enumerates the exact query patterns that trigger this tool, making the decision boundary clear. It doesn't state exclusions for non-comparison scenarios, but that is implied.

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