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

The annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, but the description adds genuinely new behavioral context the annotations cannot convey: cancellation cascades to descendant runs while already committed findings are preserved. It still omits what happens to in-flight or partial (uncommitted) work, which is the main open question for a cancel operation.

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?

A single sentence with zero waste, front-loading the action and immediately qualifying the scope and data-preservation behavior. Nothing redundant with the title or annotations.

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 values need not be described, and annotations cover the safety profile; the description supplies the cascade and preservation semantics that structured fields lack. It is largely complete for a one-parameter tool, with only the handling of uncommitted work left unspecified.

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?

One parameter (run_id, uuid) with 0% schema description coverage, so the description must carry the semantics; it does not explain run_id explicitly, though the name makes its meaning inferable. With only a single self-evident identifier, the gap is minor, landing at the minimum-viable level rather than the 0-parameter baseline.

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 (cancel) and resource (a research run, plus its descendants), which is clearly distinct from research_person, research_status, and submit_enrichment_research. It stops short of naming the sibling you would use to inspect a run before cancelling, so sibling 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?

The description never says when to cancel versus checking status with research_status first, nor what preconditions apply (e.g. must the run be in-progress). An agent can infer the basic intent from the verb, but there are no exclusions or alternatives offered.

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