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

The annotations declare readOnlyHint=true, but the description describes a state-changing operation: pending hypotheses are withdrawn so no resume will run them, a reason is recorded on each canceled attempt, and the run file comes back sealed. That is a mutation of run state, which directly contradicts the read-only annotation (destructiveHint=false is at least consistent with 'Nothing is deleted').

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 action and its scope are front-loaded, followed by the non-deletion guarantee, the precondition, and the sibling routing. The e-BH rationale is a full sentence of statistics that is informative but slightly heavy for a tool description, keeping it just short of 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 five-parameter, nested-object tool with an output schema, everything an agent needs is present: what is canceled, what is preserved, what cannot be canceled, and which sibling to use instead. Return values are covered by the output schema, so the description need not restate them.

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%, so the schema already documents run, hypotheses, reason, _files and _subject; the description only echoes the hypotheses default ('all of them, or the ones named') and that reason is recorded per attempt. Useful confirmation, but no meaning beyond the schema, so the baseline 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 names a specific verb+resource combination: withdrawing a research run's pending hypotheses, with scope spelled out (all of them, or the named ones) and the return value (the sealed run file). It is trivially distinguishable from list_research_runs, research_run_status, and resume_research_run.

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 explicitly routes the agent: 'To stop a run that is advancing in budgeted slices, stop calling resume_research_run; cancel when the pending hypotheses should never run.' It also states the exclusion 'Answered and settled hypotheses cannot be canceled,' so both when-to-use and when-not-to-use are covered.

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