List broken internal links

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

With no annotations, the description carries the full disclosure burden and delivers the key operational constraint — the required data source (live crawl or CLI dataset) and its behavior difference on desktop exports. It also clarifies the returned pair structure. It does not mention pagination behavior or ordering, but the essentials are covered.

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?

Two dense sentences with no filler; the output shape and the fix-oriented purpose are front-loaded before the data-source caveat.

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 low-complexity, single-parameter tool with no output schema, the description supplies the return shape and the critical data-source prerequisite. Nothing essential is missing, though it could briefly state the default/limit behavior to be fully self-contained.

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?

Only one optional parameter (limit) with 100% schema description coverage, so the schema already documents it fully. The description adds nothing about limit semantics, which is acceptable given the high coverage, making 3 the correct baseline.

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 ('broken internal links') and goes further by naming the exact output shape (source page → broken target pairs) and the practical intent ('which page to fix'). The crawl/export distinction also separates it from siblings like load_export and get_issues.

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 a clear prerequisite: it needs a live crawl or crawlcove-cli dataset, and notes that a desktop export instead lists broken pages because its link graph lives in the app. This is real when-to-use context, though the alternative tool to reach for in the export case is not named explicitly.

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