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

Goes well beyond the destructiveHint/readOnlyHint annotations: the queue halts at once, an in-flight item runs to its own timeout, the run settles as FAILED with a 'cancelled' reason, completed items are retained, and finished runs return run_not_live. It also flags the possible needs_confirmation response, which no annotation conveys.

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?

Four compact sentences, each carrying distinct information (state scope, motivation, queue behavior, terminal outcome). Well front-loaded, though several clauses are tightly packed.

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?

With no output schema, the description still explains the terminal state (FAILED/cancelled), retention of completed items, and the two notable return codes (run_not_live, needs_confirmation). An agent has everything needed to call it correctly and anticipate the result.

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, evalId, workspace, and approvalId are already documented. The description lightly connects to approvalId via 'May return needs_confirmation' but adds no format or sourcing detail beyond the schema, so the baseline 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 (stops) and resource (an eval run), and scopes it precisely to runs in PENDING / RUNNING / SCORING. It is clearly distinguishable from siblings like caliper_evals_runs_get or caliper_evals_runs_list 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 when-to-use context ('spending more than expected or was started by mistake') and the precondition that the run must still be live. It does not name an alternative tool, but no competing cancel tool exists in this namespace, so the guidance is functionally complete.

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