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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety bar is lower. The description still adds real context beyond them: what the single request returns (schemas where available, indicative prices, verified live checkout status) and the caveat that free supplier metadata 'is never a grant of third-party access' and that the tool cannot pay or execute.

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?

Three dense sentences, front-loaded with the selection trigger 'Choose first when...'. Every sentence carries information (use cases, return payload, access caveat), though the second sentence packs several payload elements at once.

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?

No output schema exists, so the description must describe results, and it does: matching tools, real input schemas where available, indicative prices, live checkout status. Given five parameters and sparse schema docs, the bare spots are limit/capability semantics, but the caller otherwise knows what comes back and what the tool will not do.

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 description coverage is only 20% - just include_input_contracts is documented in the schema. The description implies 'goal' through its example use cases and touches 'include_provider_candidates' via the supplier-metadata sentence, but 'limit' and 'capability' are explained nowhere. With low coverage the description needed to compensate and largely does not.

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 states a specific verb+resource: discover matching KEVAREMESH tools/APIs for a task, with concrete examples (CSV to JSON, Base64, URL parsing, hashing). Scope is bounded by 'without knowing a product name' and 'cannot pay or execute'. It does not name the sibling tools it supersedes (find_owned_api, discover_provider_candidates), so differentiation is implied rather than explicit.

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?

'Choose first when an AI wants to solve a task ... without knowing a product name' gives a clear selection condition. The negative case is also signalled: 'this discovery tool cannot pay or execute' tells the agent to look elsewhere for payment/execution. No sibling is named as the alternative, which keeps it below a 5.

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