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

With annotations already declaring readOnly, idempotent, and openWorld safety, the description adds substantial behavioral detail: type='company' pulls specific SEC EDGAR/XBRL fields (10-K revenue, net income, cash, long-term debt) with correct handling of off-calendar fiscal years; type='drug' pulls FAERS, FDA approval, and trial counts; results are sorted by primary metric; output includes paired data and citation URIs. This goes well beyond the annotation baseline.

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 well-organized, front-loading trigger phrases and immediately stating the tool's purpose. Every sentence carries meaningful detail (data sources, fiscal-year handling, sorting, citation URIs, efficiency claim). It's longer than ideal but earns its length given the tool's dual-type complexity. Slight reduction in verbiage could improve it, earning a 4 rather than a 5.

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 the tool's function, input semantics, data-fetching behavior, output format (paired data + citation URIs), and sorting logic. It also sets expectations about scale (replaces 8–15 lookups). Without an output schema, it doesn't fully specify the response structure but does give enough for an agent to infer. Missing minor details like pagination or error cases, but for its complexity, it's largely complete.

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%, so the baseline is 3. The description adds valuable context beyond the schema: it explains what each type's data sources are (e.g., latest 10-K for company, FAERS/FDA/trials for drug), provides concrete examples like ["AAPL","MSFT"] and ["ozempic","mounjaro"], and clarifies that sorting is by primary metric. This enriches the meaning of both 'type' and 'values' significantly.

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 explicit trigger phrases ("Compare X and Y") and defines the exact action: side-by-side comparison of 2–5 companies or drugs in one parallel call. It distinguishes itself from sibling tools by noting it replaces 8–15 sequential single-pack lookups, clearly positioning it as a batch comparison tool rather than a single-lookup 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?

Explicit guidance is given: "ALWAYS PREFER over sequential single-pack lookups when comparing entities," along with concrete use cases (ranking, head-to-head, which is bigger). However, it doesn't name alternative sibling tools like entity_profile or search_within directly, only refers to them generically as "sequential single-pack lookups," leaving some ambiguity for an AI agent unfamiliar with the sibling list.

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