Cancel Action Job

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

Annotations only flag destructiveHint/idempotentHint=false; the description goes well beyond by disclosing that cancellation is graceful, that a single running Revit operation finishes without interruption, that unstarted models are listed with status cancelled, and that completed changes remain committed. This tells the agent exactly what is and is not destroyed, which is precisely the behavioral burden a destructive tool carries.

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-loaded with the action, then behavior. Sentences are dense but each conveys real semantics (graceful stop, committed changes, polling target). Slightly verbose but nothing is pure 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?

An output schema exists, so return-shape explanation is not required, though the description redundantly references data.models/data.cancelled. For a destructive, non-idempotent tool the behavioral picture is essentially complete; the only real gap is undefined job_id/process_id semantics.

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 only 33%: 'document' is fully documented in the schema, but 'job_id' (required) and 'process_id' have no descriptions. The description confirms 'jobId' is the target but adds no format, source, or disambiguation meaning for it, and never mentions process_id at all, so it fails to compensate for the coverage gap.

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?

The description opens with a specific verb+resource: 'Request cancellation of an action jobId', and elaborates that process-models stops before the next model and marks unstarted models cancelled. This is concrete and distinguishable in kind. It does not, however, explicitly differentiate itself from the similarly named sibling revit_batch_cancel, so an agent must infer the boundary.

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?

It gives a follow-up action ('Poll revit_jobs for the final result'), which is useful workflow guidance. But there is no explicit when-to-use/when-not guidance, nor any routing against revit_batch_cancel, so the usage context is only implied.

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