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

Beyond annotations (readOnlyHint, openWorldHint, idempotentHint), the description reveals crucial behavioral details: it performs parallel data retrieval, pulls specific financial metrics from SEC EDGAR/XBRL for companies and FAERS data for drugs, sorts results by primary metric, and returns citation URIs. It also explains handling of different fiscal year ends, which is not obvious from 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 and front-loaded with trigger phrases, making it easy to scan. However, it could be slightly more structured (e.g., bullet points for different entity types). At 5 sentences it is concise but packs substantial information; minor improvement possible without losing clarity.

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 no output schema, the description explains return format (paired data + citation URIs) and sorting behavior. It covers data sources, entity types, edge cases (off-calendar fiscal years), and even quantifies efficiency gains. This provides a complete picture for an agent to use the tool 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?

The input schema covers both parameters with descriptions, but the description adds significant context: for 'type' it explains what data each enum value pulls (latest 10-K metrics for company, FAERS for drug), and for 'values' it clarifies expected formats (tickers/CIKs for company, drug names). It also notes min/max items, which schema already covers, but the real-world meaning is enriched.

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 comparisons of 2-5 companies or drugs. It lists trigger phrases like 'compare X and Y', 'X vs Y', 'which is bigger', and explicitly differentiates from sequential single-entity lookups by stating 'ALWAYS PREFER over sequential single-pack lookups'. This distinguishes it from sibling tools like 'entity_profile'.

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 when to use: for comparing multiple companies or drugs, with specific examples like 'rank these companies'. It advises preferring this tool over sequential single-entity lookups. It also details behavior for each type (company vs. drug), including handling of off-calendar fiscal years, giving the agent clear context for correct invocation.

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