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

Goes well beyond the annotations: states OAuth personal-connection requirement, refuses workspace keys, specifies resulting status (done, never delivered), that gates still apply, no retry and no budget reset, and the exact refusal shape (ok=false, review_requeue_refused, cause_code). This is unusually rich behavioral disclosure.

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-loads the core action, then preconditions, then idempotency and refusal behavior. Information-dense with little waste, though the parameter enumeration is packed tightly into one long sentence.

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 destructive, gated mutation with four required params and an output schema, the description covers prerequisites, side effects, idempotency, and error contract. Nothing an agent needs to call it safely 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?

With 0% schema coverage, the description fully compensates: task_id must not be an escalation id, expected_head_sha is the exact 40-character head SHA, reason is 1-2000 characters, and request_id is 1-128 chars from a stated charset. Each parameter gains meaning absent from the schema.

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 with scope: 'Return one blocked task's existing pull request to normal review.' An agent immediately grasps it acts on an existing PR, not a new run, which cleanly separates it from siblings like retry_blocked_task or replan_task.

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 strong preconditions for use (blocked task, own open PR, green/cleanly mergeable, verified DEV run) and rules out retry/budget-reset semantics. It doesn't explicitly name an alternative tool to use instead, so it stops short of a 5.

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