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

Annotations already declare destructive=true and idempotent=true, so the safety profile is known. The description adds genuinely non-obvious behavior: the stop only takes effect pre-acceptance, and an accepted provider job may continue running — a critical expectation-setting caveat an agent cannot get from the annotations.

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?

Two sentences, zero filler, with the core action and the important caveat front-loaded. Every clause carries information.

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, zero-schema-documented mutation tool with no output schema, the description covers the timing caveat well but leaves out what the caller gets back (e.g., which nodes were cancelled), how to discover attempt_id, and what happens when the call is too late. Adequate but with clear gaps.

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 0% and the three parameters carry no descriptions, so the description must compensate. It explains only the project_id + request_id pairing for prepared workflows and completely omits attempt_id, which is the alternative required branch of the oneOf — the primary path for stopping a single attempt is left unexplained.

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 (stop/cancel) and resource (an execution attempt, or undispatched nodes of a prepared workflow), which is clearly distinct from start_execution and get_execution. It does not explicitly name those siblings as alternatives, but the operation itself is unambiguous.

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?

The phrase 'before provider acceptance' gives a timing condition that implies when the tool is useful, and 'cancel undispatched nodes of a prepared workflow' hints at the prepare-then-start flow. However, no alternative is named (e.g., poll with get_execution first), and there is no explicit when-not guidance beyond the soft caveat about accepted jobs.

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