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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description adds real substance: null means unavailable rather than zero stars, records are self-reports not verified usage, vendor integrations are untested, docs-reviewed means documentation review only, and results include vendorTestingPolicy. This is meaningful caveat context beyond the structured fields, though the trust-provenance points run together and are partly duplicated in the language parameter.

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 core purpose is front-loaded in the first sentence, which is good. The remainder is a dense run-on chain of caveats, and the vendor-testing/CapaLens disclaimers largely restate what the language parameter description already covers, so not every sentence earns its place.

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?

For a read-only lookup with no output schema, the description conveys enough about returns (summaries, sample sizes, card-rating contract, AI feedback, vendorTestingPolicy) and about data trustworthiness that an agent can interpret results. It stops short of describing error behavior for an invalid or mismatched softwareId/interfaceId combination.

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?

With only 50% schema description coverage, the description compensates for the key gaps by explaining what interfaceId does, its incompatibility with capability (matching the schema's not-required constraint), and the differing response shape when it is absent. capability itself and softwareId remain undefined in both description and schema, and the language parameter's effect is only covered inside 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?

States a specific verb and resource: 'Read approved public review summaries and sample sizes,' and narrows scope further to the MCP interface card-rating contract when interfaceId is supplied. It never differentiates itself from siblings such as get_usage_observations or get_software, so an agent must infer the boundary on its own.

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?

Gives concrete selection rules for the optional parameters: interfaceId selects the exact interface card-rating contract plus separate AI feedback, 'it cannot combine with capability,' and omitting it preserves the existing software/capability response. It does not say when to prefer this tool over the sibling tools that also return software-related data.

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