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

Beyond annotations (readOnlyHint, idempotentHint), the description discloses data sources (SEC EDGAR/XBRL, FAERS, FDA), specific data fields (revenue, net income, adverse-event counts), off-calendar fiscal year handling, sorting behavior, and output format (paired data + citation URIs). This is far beyond what annotations provide and includes 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?

The description is compact yet information-dense, beginning with intuitive user phrasing, then a clear core statement, followed by type-specific details and output notes. Every clause earns its place—there is no filler or repetition. The use of em-dashes and parallel structure keeps it scannable.

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 two-parameter tool with no output schema, the description thoroughly covers input semantics, data sources, per-type behavior, sorting, and return format, while explaining why this tool is preferable to alternatives. It is entirely sufficient for an agent to invoke it correctly across the full range of supported use cases.

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?

The schema only names 'type' and 'values' with minimal descriptions. The description enriches both parameters by explaining exactly what each type retrieves ('type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt') and what values should contain (2–5 tickers/CIKs or drug names). It also adds fiscal year nuance that neither schema nor annotations cover.

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 opens with concrete query examples ('Compare X and Y', 'which is bigger') and explicitly states 'side-by-side comparison of 2–5 companies or drugs in ONE parallel call.' It clearly distinguishes itself from sibling single-entity tools like entity_profile by emphasizing that it replaces 8–15 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?

The description provides explicit trigger phrases and a strong directive: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also gives type-specific guidance for company vs. drug and explains that comparisons are sorted by primary metric, giving the agent confidence in when and how to use it.

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