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

The description adds significant behavioral context beyond annotations: for companies, it explains data sources (SEC EDGAR/XBRL), specifics (revenue, net income, cash, debt), and smart handling of fiscal years. For drugs, it lists adverse-event counts, FDA approvals, and trial counts. It also mentions sorting by primary metric and inclusion of citation URIs. Annotations already indicate readOnly, idempotent, non-destructive, and open-world, but the description enriches the behavioral understanding.

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 packed with useful information but is somewhat lengthy. However, every sentence adds value and it is front-loaded with trigger phrases. It could be slightly more concise, but the density of information justifies the length.

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 complexity of the tool (two entity types, multiple data sources, sorting, citations), the description covers all aspects: what data is retrieved, how it is processed, and what the output contains (paired data + citation URIs). It also explains the sorting behavior. No output schema exists, but the description compensates adequately.

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 adds rich semantic meaning for both parameters. For 'type', it explains the implications of 'company' vs 'drug' (what data is pulled). For 'values', it clarifies that for companies these are tickers/CIKs, and for drugs they are names. It also specifies the allowed range (2-5 items) which is redundant with schema but reinforces it. The description goes beyond schema documentation.

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's purpose: side-by-side comparison of 2-5 entities (companies or drugs). It provides multiple trigger phrases like 'Compare X and Y' and 'X vs Y', and distinguishes from siblings like entity_profile (which likely handles single entities). The verb+resource is specific and unambiguous.

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 guidance on when to use this tool. It implies not to use it for single entity lookups, but does not explicitly list exclusion cases or mention alternative tools for single entities.

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