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

Annotations already declare readOnly/openWorld/idempotent/destructive hints, but the description adds behavior not captured by annotations: sourcing from SEC EDGAR/XBRL, handling off-calendar fiscal years (AAPL Sep, NVDA Jan), sorting by primary metric, and returning citation URIs. No contradiction with 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 dense but purposeful. It front-loads the core purpose and usage trigger phrases, then adds data source specifics, sorting behavior, and return format. Each sentence earns its place, though the long list of example phrasings makes it slightly verbose compared to a minimal 'Compares entities' statement.

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?

With only 2 parameters and no output schema, the description fully covers the tool's context: what data is pulled for each type, how results are sorted, what is returned (paired data + citation URIs), and the advantage over sequential lookups. It leaves no significant gaps for the agent to invoke it correctly.

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% (2 params well-described via enum and array details), but the description adds meaning beyond the schema: type='company' pulls specific financial metrics from latest 10-K, type='drug' pulls FAERS/trial counts, and values clarification for tickers/CIKs vs drug names. This enriches parameter understanding without duplicating 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 uses a clear verb ('compare') with specific examples of user phrasing ('X vs Y', 'which is bigger') and explicitly states the resource (2–5 companies or drugs). It distinguishes from sibling tools like entity_profile by emphasizing side-by-side comparison in ONE parallel call vs 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?

It explicitly states when to prefer this tool: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and quantifies the benefit ('Replaces 8–15 sequential lookups'). It also gives context for when to use it (comparing entities) without ambiguity.

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