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

Annotations only declare readOnlyHint=false / destructiveHint=false / idempotentHint=false; the description goes further by disclosing the permission requirement (org admins), the blast-radius boundary ('reviews already posted do not change'), and the installation-scoped blast radius. It does not say what happens when the relationship was never stated (idempotentHint=false suggests a failure mode), leaving one behavioral 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?

Front-loaded with the action and resource, then the constraints; every clause carries information about scope, permissions, or alternatives. It is somewhat over-packed into one long sentence and repeats the order-independence point already in the schema, which is a minor waste.

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 3-required-param mutation tool with no output schema and non-destructive annotations, the description covers authorization, side-effect boundaries, scope limits, and the read-side companion tool. The only shortfall is the undefined behavior when the relationship does not exist, which matters given idempotentHint=false.

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 100%, and the schema already documents installation_id ('Numeric id ... as a string'), repository ('owner/name'), and the relationship's symmetry. The description's 'in whichever order each was stated' merely restates the schema's symmetry note rather than adding new semantic detail, so the baseline of 3 applies.

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 pair ('Stop AI code reviews relating two repositories', 'removes the stated relationship between them') and scopes it to one GitHub App installation. It clearly distinguishes itself from the sibling list_related_repositories (read-side) and from relate_repositories (the inverse), so an agent can route correctly without opening either schema.

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 eligibility gate ('Organisation admins only'), an explicit negative case ('this cannot unrelate applications installed on the same cluster - those are related with nothing stated'), and names the alternative tool to consult state ('list_related_repositories shows what is stated'). Both when-to-use and when-not-to-use are covered, which is rare.

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