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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds significant behavioral context: results are sorted by primary metric (so 'largest' reads off the top), off-calendar fiscal years are handled correctly, and data sources are specified (SEC EDGAR/XBRL for companies, FAERS/FDA/trials for drugs). 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 a single dense paragraph but is front-loaded with the most important information (triggers, purpose, usage advice). It covers all key points without redundancy. A minor improvement would be to break it into bullet points for easier parsing, but it remains concise and efficient.

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, multiple data sources, sorting, citation URIs), the description covers the main aspects: what it returns, data sources, and sorting behavior. There is no output schema, but it mentions the return format (paired data + URIs). It lacks details on potential errors or rate limits, but annotations (openWorldHint) imply data may vary over time. Overall, it is sufficiently complete for an agent to use effectively.

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 still adds value: it explains the type parameter with examples ('company' vs 'drug'), and the values parameter gives concrete examples like ['AAPL','MSFT'] and ['ozempic','mounjaro'] along with constraints (tickers/CIKs for companies, names for drugs). This goes beyond the schema's short 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 starts with user-facing trigger phrases like 'Compare X and Y' and explicitly states the tool performs side-by-side comparison of 2–5 companies or drugs in a single parallel call. It distinguishes itself from sequential single-pack lookups (e.g., entity_profile) and specifies what each entity type returns (financials for companies, adverse-event counts for drugs). This makes the purpose highly specific and actionable.

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 includes a clear preference directive: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' This tells the agent when to use this tool over alternatives. The sibling list includes entity_profile, which is the direct alternative for single-entity lookups, so the guidance is well contextualized.

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