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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds rich behavioral detail: performs one parallel call, pulls specific financial/drug data from named sources, handles off-calendar fiscal years, sorts by primary metric, returns paired data with citation URIs, and replaces 8–15 lookups. No contradiction 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 dense but every sentence provides value: trigger phrases, explicit usage preference, data source details, edge cases, sorting, and output format. It is front-loaded with purpose. While on the longer side, it avoids redundancy and remains well-organized.

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?

For a tool with 2 simple parameters and no output schema, the description covers practically all needed context: data sources, entity-specific behavior, sorting rule, output content (paired data + citation URIs), and performance benefit. The off-calendar fiscal year handling is particularly valuable. Nothing significant is missing.

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 goes further. It explains what each type ('company' vs 'drug') does with concrete data fields (10-K revenue, FAERS counts), gives examples for the values array (['AAPL','MSFT'], ['ozempic','mounjaro']), and clarifies constraints (2–5 items). This adds meaning 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 states the tool performs 'side-by-side comparison of 2–5 companies or drugs in ONE parallel call' — a specific verb and resource. It also lists trigger phrases ('X vs Y', 'which is bigger', 'rank these companies') and distinguishes itself from sequential single-entity 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?

The description explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', giving clear when-to-use guidance and naming the alternative to avoid. It also implies when not to use (single-entity lookups) and provides context for both company and drug entity types.

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