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

Beyond the readOnly/idempotent annotations, the description reveals significant behavioral details: company type pulls specific SEC EDGAR/XBRL fields from latest 10-Ks, handles off-calendar fiscal years (AAPL, NVDA examples), drug type pulls FAERS counts, and results are sorted by primary metric with citation URIs. This goes far beyond what annotations provide.

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: it leads with user-intent phrasing, then explains behavior, sources, sorting, and output format. Every sentence carries useful information, though the length is above the bare minimum and contains some redundancy (e.g., 'ONE parallel call' and 'ALWAYS PREFER over sequential' overlap).

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 no output schema, the description takes on the burden of explaining return behavior, and it does so: sorted results, paired data, and citation URIs per entity. It also covers entity type specifics, cardinality constraints, and examples. It could mention potential errors or rate limits, but for the tool's complexity it is 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?

The input schema already describes both parameters with 100% coverage, so the baseline is 3. The description adds semantic depth by explaining how the 'type' enum changes data sources and metrics ('company' pulls financials, 'drug' pulls adverse-event/trial counts), and gives realistic examples for 'values' (tickers, drug names). This adds value beyond the 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 begins with concrete query patterns ('X vs Y', 'which is bigger') and explicitly states the tool performs side-by-side comparison of 2–5 entities in a single parallel call. It clearly distinguishes from sequential single-pack lookups and lists two supported entity types, making the purpose unambiguous.

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 gives an explicit directive: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' This tells the agent when to use the tool, and it contrasts with the alternative of multiple sequential lookups, though it does not name a specific sibling tool like entity_profile as the alternative.

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