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

With no annotations, the description carries the full burden and does well: it discloses the false-negative risk ('empty result only means no known issues were detected') and that the check is pattern-based rather than semantic. It does not describe the shape of a non-empty result (issue list, severities, line references), which is the remaining gap.

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?

Purpose is front-loaded in the first sentence, followed by the detection list, then the limitation caveat, then the call to action. Every sentence serves a purpose; the pattern enumeration is slightly long but earns its place by setting expectations.

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 one-parameter, no-output-schema lint tool, the definition covers what it does, its limits, and when to call it. Only the result format for a non-empty response is unstated, which is a minor omission given no output schema exists.

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 coverage is 0% for the single 'code' parameter, so the description must compensate. It implies the input is component or page source, but does not say whether a full file (with imports/export) or a fragment is expected, nor whether page vs component code changes behavior.

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+resource (check Duck Framework component or page code) and enumerates the concrete mistake classes it detects (bad component/page imports, Heading usage, leading-underscore methods, separator comments). No sibling tool performs code linting, so an agent can route here unambiguously.

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 an explicit trigger: 'Run this on generated component code before presenting it as final.' It also sets a negative boundary by saying it is not a complete correctness validator. It does not name an alternative tool for deeper validation, but no sibling offers one.

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