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

Annotations already mark it as read-only, open-world, idempotent. Description adds valuable behavioral details: handles off-calendar fiscal years correctly, sorts results by primary metric, returns citation URIs. No contradictions.

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?

Informative and well-structured, front-loading triggers and key instructions. However, slightly verbose with some redundancy ('off-calendar fiscal years handled correctly' example could be trimmed). Still highly 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?

For a tool with no output schema, the description fully covers return data: paired data, sorted by metric, citation URIs per entity. Sufficient for agent to understand what to expect. No gaps given the tool's complexity.

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 has 100% coverage with descriptions. The description adds meaning beyond schema: explains what data each type pulls (company: financials from SEC; drug: FAERS, FDA approvals, trial counts) and gives example value formats (tickers for company, drug names).

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 compares 2-5 entities (companies or drugs) side-by-side in one parallel call, with specific data per entity type. It distinguishes from sequential lookups and 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?

Explicitly prescribes usage for comparison queries ('Compare X and Y', 'X vs Y', etc.) and states preference over sequential lookups. Provides natural language triggers and scope (2-5 entities). No explicit exclusions but clear intended context.

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