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

With no annotations, the description carries the full burden and does fairly well: it discloses the permission requirement (canEdit on the issue), the boolean return semantics including the race condition where the run is no longer Working because a person cancelled it, and that reason is discarded for Done. It doesn't say whether finishing is idempotent or what happens to the run's subsequent state, which keeps it out of 5 territory.

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?

Three tight sentences, front-loaded with the action and its outcomes, then the false-return semantics, then the permission prerequisite. No filler.

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 mutation tool with no annotations and no output schema, the description covers the two things an agent most needs: the permission prerequisite and the meaning of the boolean return value, including the cancellation race. The remaining gap is what the run transitions to after a Done vs Failed finish and whether reason is surfaced anywhere.

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%, so runId, state, and reason are already fully documented in the schema, including the enum values and the max length. The description adds essentially nothing parameter-specific beyond what the schema says, 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 ('Finishes') and resource ('a Working agent run') with the two terminal outcomes it can produce (Done or Failed), which is well beyond a restatement of the name. It doesn't explicitly name cancel_agent_run as the sibling that produces the false path, but the reference to a person cancelling the run effectively implies the division of labor.

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 real invocation context: the run must currently be Working, and a false return means someone else cancelled it, so the agent should stop working. It lacks an explicit 'do not call this if...' or a direct pointer to cancel_agent_run, but the condition that selects this tool over that one is inferable.

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