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

Annotations declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. Description adds rich detail: sources (SEC EDGAR/XBRL, FAERS), metrics (revenue, net income, cash, debt, adverse events, trials), and behavior like off-calendar fiscal year handling and sorting by primary metric. 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?

Dense with information but well-structured: starts with example triggers, then explains behavior for each type. Every sentence adds value, though slightly verbose with the off-calendar note.

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?

Covers entity types, data sources, metrics, sorting, and return format (paired data + citation URIs). No output schema, but description adequately summarizes returns. Complete for a comparison tool.

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%, and description adds meaning: explains type='company' vs 'drug' data sources, and describes array values (tickers/CIKs for company, names for drug) with limits (2-5 items). This surpasses the schema's bare descriptions.

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 does side-by-side comparisons of 2-5 companies or drugs, with explicit example phrases. It distinguishes from sibling tools like entity_profile by focusing on multi-entity comparison.

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 instructs to 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', providing clear when-to-use guidance and example queries.

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