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

Beyond the readOnly/idempotent annotations, the description discloses specific data sources (SEC EDGAR/XBRL for companies, FAERS/FDA for drugs), exact fields pulled (revenue, net income, cash, long-term debt), sorting behavior, and output details (paired data + citation URIs). This substantially exceeds annotation coverage and gives the agent a clear model of tool behavior.

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?

While long, every sentence carries meaningful information: trigger phrases, the parallel-call advantage, type-specific data sources, sorting, and output format. The structure front-loads the primary purpose and usage, then details data behavior. No redundant or filler content is present.

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, 2–5 items, multiple data dimensions, no output schema), the description is remarkably complete. It covers inputs, data sources, fiscal-year edge cases, sorting, and output format, leaving no major ambiguity for an agent selecting or invoking the tool.

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 already covers 100% of parameter meaning, so baseline is 3. The description adds value by explaining the semantics of each type: for company it pulls 10-K financials, for drug it pulls adverse-event and trial counts. It also contextualizes the values parameter with examples (tickers vs drug names) and clarifies that 'largest'/'most' maps to the sort order, going beyond schema 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 clearly identifies the tool as performing side-by-side comparisons of 2–5 companies or drugs, with specific trigger phrases ('Compare X and Y', 'X vs Y'). It distinguishes itself from siblings by explicitly noting it should be preferred over sequential single-pack lookups and that it replaces 8–15 lookups, making the purpose unique and 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 provides explicit guidance on when to use the tool (trigger phrases, comparison intent) and when not to (sequential single-pack lookups). It also gives type-specific contextual instructions, such as handling off-calendar fiscal years for companies, and notes that results are sorted by primary metric, which helps the user interpret output correctly.

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