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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context beyond annotations: it specifies data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), notes correct handling of off-calendar fiscal years, and explains results are sorted by primary metric. It does not address error handling or rate limits, but the core behavioral traits are transparent.

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 paragraph that efficiently packs examples, purpose, usage guidance, and data details. It is front-loaded with query examples and ends with impact ('replaces 8-15 sequential lookups'). Every sentence serves a purpose, though it could be slightly better structured (e.g., bullet points).

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 two parameters and no output schema, the description covers: what it does, when to use, what data is returned (paired data with citation URIs), and key behaviors (sorting by metric). It does not detail the response format, but 'paired data' and 'URIs' give a decent mental model. Missing specifics on how 'primary metric' is determined, but overall complete enough.

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%, with clear descriptions for 'type' and 'values'. The description reinforces that 'type' determines the data source (company vs. drug) and adds detail on which financial metrics are pulled for companies (revenue, net income, etc.) and which counts for drugs (adverse events, FDA approvals, trials). This adds context but does not fundamentally extend schema info.

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 in one call, with specific examples of queries (e.g., 'compare X and Y', 'rank these companies'). It distinguishes itself from sequential single-entity lookups and sibling tools like entity_profile by emphasizing that it replaces 8-15 sequential 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 advises 'ALWAYS PREFER over sequential single-pack lookups when comparing entities,' providing clear when-to-use guidance. It also includes query patterns that trigger this tool (e.g., 'which is bigger', 'head to head'), helping the agent recognize appropriate contexts.

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