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

Annotations indicate destructiveHint=true, so the description correctly implies a mutating operation. It adds useful behavioral context: the tool is rate-limited per site and returns an error with wait time when the cooldown is active, which is not in annotations. It could disclose what 'remap' means in terms of side effects (e.g., does it replace existing owned pages or append?), but the rate-limit behavior is a significant addition beyond annotations.

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 two sentences with no wasted words. The core action is front-loaded ('Re-crawl the project website and refresh its owned pages'), followed by usage guidance and a key behavioral caveat (rate-limiting). Perfectly sized for the tool's simplicity.

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?

This is a simple single-parameter tool with no output schema. The description covers the purpose, when to use, and a critical behavioral detail (rate-limit). It does not mention what the success response looks like, but with no output schema, that's less critical. For a mutation tool, it could state what the outcome is (e.g., 'owned pages are updated'), but the rate-limit note compensates. Overall, it's nearly complete for an agent to invoke correctly.

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 0%, meaning the schema provides no description for projectId. The description does not explain the parameter semantics beyond the obvious 'projectId' identifier. However, the parameter is a UUID with a clear format, and the tool's purpose implies it refers to the project whose asset should be remapped. Since there is only one parameter and its meaning is inferable from context, a score of 3 is appropriate; the description could add more (e.g., 'the ID of the project whose website asset to re-crawl') but the gap is minor.

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 clearly states the tool's function: re-crawling the project website and refreshing owned pages. It explicitly names the resource (project website) and the action (re-crawl, refresh), and differentiates itself from siblings like resync_asset_profile and update_asset_profile, though it doesn't name them directly. However, the use case with get_project_asset and mappingStatus is highly specific and distinguishes it from other mutation tools.

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?

The description provides explicit when-to-use guidance: when get_project_asset shows mappingStatus 'error' or owned pages look stale. It also mentions rate-limiting and the error response that names wait time, which helps the agent decide whether to call it or wait. While it doesn't explicitly say 'do not use when X', the conditions imply the alternative (get_project_asset) and the cooldown error guides the agent away from repeated calls.

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