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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is structured. The description adds the non-obvious post-condition that existing results remain available for inspection, which materially narrows how destructive the call actually is. It does not say what happens to an in-flight run or whether cancelling a finished run errors.

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 short sentences, zero filler, with the action and its gating condition front-loaded before the aftermath note. Every sentence carries distinct 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?

With rich annotations (destructive, idempotent, closed-world) and an output schema present, the description only needs purpose, invocation gate, and side-effect scope, and it covers all three. Return values and parameter formats are correctly left to structured fields.

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 50%: organization_id is documented in the schema, while run_id relies on its name and UUID format. The description only reinforces that a single run is targeted, adding little beyond the schema. Baseline 3 is appropriate given the partial coverage.

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 ('Cancel one durable analysis run'), and the word 'one' plus 'durable analysis run' distinguishes it from bulk operations and from session/study cancellation siblings. It never names an adjacent sibling such as resume_research_analysis or get_research_analysis, so differentiation is implied rather than explicit.

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?

'only when the user requests it' gives an explicit gating condition for invocation rather than leaving timing to inference. It stops short of naming alternatives or stating when-not to use it (e.g., completed runs, or use resume_research_analysis instead), so no exclusions are covered.

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