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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description goes further by disclosing data sources (SEC EDGAR/XBRL for companies, FAERS/FDA for drugs), handling of off-calendar fiscal years, sorting by primary metric, and the return of paired data with citation URIs. This adds substantial behavioral context beyond the structured 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 front-loaded with trigger phrases and usage direction, followed by type-specific behavior and output details. Every sentence earns its place, providing dense, non-redundant information. Despite its length, it remains well-structured and efficient for the complexity of the tool.

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 absence of an output schema, the description covers essential return details: data types, sorting, and citation URIs. It also explains critical edge cases like off-calendar fiscal years. However, the exact response structure ('paired data') is somewhat vague, leaving some ambiguity about the precise format the agent will receive.

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 enriches the 'type' parameter by specifying exactly what data each enum value retrieves ('company' pull financials, 'drug' pulls adverse-event counts). It also clarifies the values parameter through examples ('AAPL, MSFT' vs 'ozempic, mounjaro'), adding semantic meaning beyond the 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 begins with trigger phrases ('Compare X and Y', 'X vs Y') and explicitly states 'side-by-side comparison of 2–5 companies or drugs in ONE parallel call'. It clearly identifies the resource (companies/drugs) and the action (comparison), while distinguishing itself from single-entity lookups by emphasizing 'ALWAYS PREFER over sequential single-pack 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 provides explicit usage guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and lists concrete comparison queries. It also outlines what data is returned for each type (company vs drug), giving clear context for when to invoke this tool instead of alternatives.

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