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

The description provides extensive behavioral detail beyond the annotations: for 'company' it specifies it pulls latest 10-K data (revenue, net income, cash, debt) with correct off-calendar fiscal year handling; for 'drug' it pulls FAERS counts, FDA approvals, trial counts. It also notes results are sorted by primary metric and that citation URIs are returned. This fully informs the agent of what to expect without contradicting the readOnlyHint, openWorldHint, or idempotentHint 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 front-loaded with trigger phrases and quickly gets to the purpose. It is comprehensive but slightly verbose in repeating the efficiency gain ('in ONE parallel call' and 'Replaces 8–15 sequential lookups'). Still, every sentence adds value, and the overall structure is logical. Minor improvements could tighten phrasing.

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?

Given the tool has only 2 parameters and no output schema, the description fully explains input expectations, behavior for both entity types, sorting behavior, and output format (paired data + citation URIs). It even covers edge cases like off-calendar fiscal years. An agent has all the information needed to invoke the tool correctly and interpret results.

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 input schema already covers both parameters with descriptions (type enum and values array). The description adds valuable context: examples of values ('AAPL','MSFT' for companies; 'ozempic','mounjaro' for drugs) and constraints (2-5 items). This goes beyond the schema's minimal descriptions, though the schema itself is 100% covered. The added information is helpful but not essential.

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 performs side-by-side comparisons of 2-5 companies or drugs in one call. It provides example trigger phrases ('X vs Y', 'which is bigger') and distinguishes itself from single-entity lookup tools like entity_profile. This makes the purpose unambiguous and easily matched to user intent.

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 explicitly says to 'ALWAYS PREFER over sequential single-pack lookups when comparing entities,' giving clear guidance on when to use. It does not explicitly list cases when not to use (e.g., single entity), but the context implies it. Alternatives like entity_profile exist for single lookups, and the description indirectly suggests they are inferior for comparisons.

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