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

The description discloses specific data sources (SEC EDGAR/XBRL, FAERS), metrics (revenue, net income, cash, long-term debt, adverse-event counts), edge-case handling (off-calendar fiscal years), sorting behavior, and return format (paired data + citation URIs). This goes far beyond the annotations' read-only hints.

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 well-structured, opening with common user phrasings, then stating core function, preference rule, and per-type details. Every sentence provides actionable information without redundancy.

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 fully covers return values (paired data + citation URIs), sorting order, entity count limits, and data sources. For a comparison tool with 2 parameters, this is complete and leaves no critical ambiguity.

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?

Despite full schema coverage, the description adds deep semantic value by explaining what each type ('company' or 'drug') returns, including data metrics and fiscal year handling. This clarifies the enum values beyond the schema, compensating for no output schema.

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 it performs side-by-side comparison of 2–5 companies or drugs in a single call, with specific examples of user intent. It distinguishes this from sequential single-pack lookups by emphasizing 'ALWAYS PREFER', making the tool's purpose unmistakable.

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?

It provides explicit guidance to prefer this tool over sequential lookups when comparing entities and lists trigger phrases. However, it does not name alternative tools like entity_profile for single-entity lookups, so the exclusions are less explicit than the highest bar.

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