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

Goes well past the annotations by disclosing external side effects that readOnlyHint=false alone does not convey: PR Explanation stores a private explanation and posts nothing to GitHub, while Code Review posts review comments on the pull request. It also explains retry behavior — the same idempotency key returns the same execution — which makes the idempotentHint concrete.

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 action, then prerequisites, then per-task side effects, then the invocation guard and retry behavior. Four sentences, each carrying distinct operational information with no restatement of the name or title.

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, open-world, nested-parameter tool with an output schema, the description covers the remaining risk surface: setup prerequisite, what each task does to external state, when invocation is authorized, and idempotent retry. Return values are handled by the output schema, so nothing material 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 80%, so the schema already documents task_id, pull_request fields, organization_id, and idempotency_key. The description reinforces the exact-revision semantics of expected_head_sha and the reuse rule for the idempotency key but adds nothing about the audience enum or its PR-Explanation-only restriction beyond what the schema states. Baseline 3 is appropriate.

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 ("Start one first-party task") plus two scoping constraints: the task must come from list_tasks and must target an exact pull-request revision. The two task types are distinguished by name (PR Explanation vs Code Review), so an agent can tell what it is starting without opening a 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 preconditions and routing: verify the repository is connected and call get_started with the same organization_id if unsure, and start only after the user explicitly asks in the current turn. Both alternatives (list_tasks, get_started) are named with the condition that selects them.

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