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

Annotations already declare readOnlyHint and openWorldHint, so the description doesn't need to restate safety. It does add useful context by explaining the link-gap ranking behavior and the project_id source. However, it gives no further operational details such as output scope, pagination, or what 'may use lookups' actually means.

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 short and front-loads the tool's purpose before explaining the key parameter. The phrasing 'protect, and fix' is vague and 'may use lookups' is elliptical, but overall it avoids unnecessary repetition and stays appropriately compact.

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?

With an output schema present, return values don't need to be described. The required parameter and optional link-gap mode are explained. However, the description names three recommendation categories — outreach, protect, fix — and only elaborates on the outreach/link-gap case, leaving significant ambiguity about what the other modes produce.

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 50%, and the required project_id is undocumented in the schema itself. The description fills that gap by identifying project_id as a ranking id from list_projects. competitor_domain semantics are covered both in the schema and again in the description, so all parameters are meaningfully explained somewhere.

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 clear topic: 'Backlink outreach, protect, and fix recommendations for a project.' It is more specific than a tautology and names the link-gap mode, which helps distinguish it from raw profile tools like get_backlink_profile or get_new_lost_backlinks. However, 'protect' and 'fix' are left undefined, and it doesn't explicitly differentiate itself from sibling 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 gives a concrete condition: pass competitor_domain to get link-gap domains that link to a rival but not to the user. It also explains that project_id comes from list_projects. But it does not state when to prefer this tool over sibling backlink or analysis tools, nor when not to use it.

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