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

readOnlyHint=true already tells the agent this is a safe read. The description earns credit for disclosing that an unmatched protein returns an empty list rather than an error, which is genuinely useful behavioral context. Beyond that it says little about result size limits, ordering, or aggregation across suppliers, and the existing output schema covers the return shape.

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 and front-loads the resource and scope before the caveats. The field enumeration in the first sentence is a dense list, but each element maps to actual output content rather than being 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?

With an output schema present and readOnlyHint declared, the description only needs to cover intent, scope, and edge behavior, which it does via the empty-list rule and the stock-vs-made-to-order distinction. Minor residual gaps around result ordering or limits are tolerable given the output schema and single simple parameter.

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?

There is a single parameter with 100% schema coverage, and the schema already explains 'Protein symbol or alias, e.g. KRAS'. The description adds no additional semantics such as alias resolution behavior, case sensitivity, or whether partial matches are accepted, so the baseline for fully documented parameters applies.

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 names a specific resource and scope: off-the-shelf products for a protein, with the returned fields enumerated (supplier, catalog number, product name, species, expression host, size, price). It clearly separates stock items from made-to-order, so an agent can tell what kind of data this returns. It stops short of naming siblings like find_cro or find_protocol, but their domains are distinct enough that confusion is unlikely.

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?

'Stock items, not made-to-order' and 'only products the page actually lists' establish result-scope exclusions, which implicitly tells an agent when this tool is the wrong source. There is no explicit when-to-use framing or routing to an alternative for made-to-order or custom-supplier needs, so selection guidance is inferred rather than stated.

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