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

Annotations only carry readOnly=false, idempotent=false, destructive=false; the description goes well beyond them by disclosing admin-only authorization, the GitHub App installation reachability check that can refuse the call, the installation-token fetch semantics, symmetry (no mirror to add), the no-op on re-stating a pair, and the return value. The 're-stating changes nothing' phrasing is mildly at odds with idempotentHint=false, but it describes stored state rather than a serious contradiction.

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 and the core use case are front-loaded, and the dense single block is almost entirely information-bearing. It is slightly overlong with a second clause explaining the installation-token rationale, but no sentence is filler and structure is logical.

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 mutating, admin-scoped tool with no output schema and minimal annotations, the description covers authorization, validation/failure conditions, idempotency behavior, symmetry semantics, and the return value. Nothing an agent needs in order to call it correctly is missing.

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 100%, so the schema already documents owner/name formats and where installation_id comes from (baseline 3). The description adds materially more: the symmetric nature that makes repository vs related_repository interchangeable, and the constraint tying installation_id to a live installation listing that the review fetches with — meaning the parameter is not arbitrary.

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 (state a relationship), resource (two repositories), and the downstream purpose (AI code review reading each other), and clearly distinguishes it from siblings like unrelate_repositories and list_related_repositories. An agent can tell exactly what this tool establishes without opening any 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 explicit when-to-use cases (client and its API, shared library, repo outside Ankra's deploy) and an explicit when-not (applications on the same cluster are already related with no statement needed). The deploy-graph boundary and the alternative it implies are spelled out, leaving nothing to inference.

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