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

The description discloses key behavioral traits beyond annotations: it pulls data from specific sources (SEC EDGAR/XBRL for companies, FAERS/FDA/clinicaltrials for drugs), handles off-calendar fiscal years correctly, returns sorted results by primary metric, and includes citation URIs. Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior, and the description adds valuable context without contradiction.

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 and well-structured, using parenthetical examples and short clauses. It is front-loaded with natural language queries that the tool handles, and every sentence adds value without redundancy. It efficiently communicates purpose, usage, and returned data.

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?

Despite having no output schema, the description fully explains what is returned (paired data and citation URIs) and covers both entity types. It addresses edge cases like off-calendar fiscal years and sorting behavior. For a comparison tool with two parameters and clear return expectations, the description is complete and leaves no significant gaps.

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%, but the description adds significant semantic value beyond schema: it explains what data is retrieved for each type (e.g., latest 10-K revenue/net income/cash/debt for companies; adverse events/approvals/trials for drugs), the sorting behavior, and how to interpret the response. This helps the agent understand the parameters' meaning and usage effectively.

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 explicitly states the tool performs side-by-side comparisons of 2–5 companies or drugs, using clear verb phrases like 'Compare X and Y', 'which is bigger', 'rank these companies'. It distinguishes itself from sibling tools like entity_profile (single entity) and sequential lookups, making its purpose unmistakable.

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 strongly recommends using this tool over sequential single-pack lookups when comparing entities, and provides context for when to use it. However, it does not explicitly mention when not to use it or suggest alternative sibling tools for different types of comparisons (e.g., comparing other entity types), so guidance is not exhaustive.

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