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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) already establish safety, but the description adds non-obvious behavior: it pulls specific metrics (10-K revenue/net income/cash/debt for companies; FAERS/approval/trial counts for drugs), sorts results by primary metric, and returns paired data with 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 concise given the tool's complexity, front-loaded with trigger phrases and usage guidance. Every sentence adds value (trigger phrases, preference directive, data sources, sorting behavior, return shape, efficiency claim). No filler.

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?

The description covers both entity types, their data sources, fiscal year nuances, sorting behavior, and return value format (paired data + citation URIs). Given no output schema, this sufficiently explains what to expect. It addresses edge cases (off-calendar fiscal years) and performance (replaces 8–15 lookups), making it complete for an agent to select and invoke.

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 descriptions are thorough, giving full coverage (100%) of type and values. The description enriches these by specifying what each type retrieves (e.g., 'type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt') and clarifies the values format (tickers/CIKs vs drug names). This goes beyond the schema, though the core parameter names are already well-described.

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 explicitly states the tool performs side-by-side comparisons of 2–5 companies or drugs in one parallel call, using specific trigger phrases like 'X vs Y' and 'which is bigger'. It clearly distinguishes itself from sequential single-pack lookups and mentions it replaces 8–15 sequential calls, setting it apart from sibling tools like entity_profile.

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 provides explicit guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also clarifies when to use company vs drug types and notes off-calendar fiscal year handling. This gives clear context for selection and excludes alternatives.

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