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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the basic safety profile is covered. The description adds real value beyond that: irreversibility, the consequence for completed work, owner-only/paid access, the subscription gate with a subscribe link, and the fact that no live orders or model inference are involved. Return shape and any partial-cancellation behaviour remain unstated.

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?

The irreversible consequence is front-loaded in the second clause and no sentence is superfluous. The closing access clause ('keyless: subscription_required with a subscribe link') is telegraphic and slightly awkward to parse, which keeps it from a 5.

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 single-parameter destructive tool with no output schema, the description covers the essentials: what is destroyed, that it is irreversible, who may call it, and what access tier is required. Only the response behaviour after a successful or failed cancel is left open, which is minor given the absence of an output schema.

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 100% and the single run_id parameter is already documented as a 32-character lowercase hex study ID from an owned run result. The description adds no syntax, format, or ownership semantics beyond what the schema provides, so the baseline of 3 applies.

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 and resource — 'Cancel a saved research job' — which is unambiguous. It does not explicitly contrast itself with the adjacent siblings research_paper_pause or research_run_read, so it stops short of full sibling differentiation.

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?

'Cancellation cannot be undone; completed work may need a new submission' implies when the tool is appropriate (only for jobs you want to abandon) and hints at the re-submission path. However, it never names an alternative tool or states a when-not-to-use condition explicitly, leaving the agent to infer the choice against research_run_list or research_paper_pause.

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