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

Adds significant detail beyond annotations: describes data sources (SEC EDGAR/XBRL, FAERS), specific metrics (revenue, net income, cash, debt, adverse events, trial counts), sorting by primary metric, and citation URIs. All consistent with readOnly, openWorld, and idempotent 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?

Single paragraph efficiently conveys purpose, usage, behavior, and examples. Front-loaded with common queries, no redundant sentences.

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?

Returns are partially described (metrics, sorted, citations) but no output schema. For a tool with two modes, the description covers key aspects like fiscal year handling and preferred usage, though exact data shape for each type could be more explicit.

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 already has clear descriptions for type and values (with enum and min/max items). Description adds concrete examples for both company tickers and drug names, enhancing usability. With 100% schema coverage, this is a valuable addition.

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 defines the tool as performing side-by-side comparisons of 2–5 companies or drugs, with examples like 'compare X and Y' and 'head to head'. It distinguishes from siblings like entity_profile by recommending preference over 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?

Explicitly states when to use: for comparisons of 2–5 entities, and when to prefer over sequential lookups. Provides example queries and explains behavior for company vs drug types.

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