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

Goes beyond the annotations by disclosing two behavioral facts an agent cares about: already retained results stay available after cancellation, and repeated calls are idempotent (confirming idempotentHint). It still does not say whether the underlying work stops immediately or whether the returned state can be 'cancelled' vs 'completed'.

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 tight sentences, front-loaded with the action and return, followed by the precondition and idempotency note. 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?

Output schema exists, so return values need not be described. Ownership, retention of results, and idempotency are covered; the only omission is relationship to research_status/other job lifecycle siblings.

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 100% and the single parameter is fully documented there, so the schema carries the load. The description's 'owned research job ID' only echoes the schema's 'Owner-scoped research job ID' without adding format, source, or lookup details.

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: request cancellation of a research job and return its state. A reader can distinguish it from research_start/research_results, though it never explicitly names research_status as the non-cancelling alternative for polling job state.

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 one precondition ('Pass an owned research job ID'), which tells the agent the ID must belong to it. However, there is no when-to-use vs when-not guidance and no explicit contrast with research_status for agents that merely want job state without cancelling.

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