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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal one important non-destructive guarantee ('without cancelling earned obligations'), but it omits critical behavioral details such as concurrency control via expectedVersion, idempotency handling, whether closing is reversible, and what side effects occur.

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 description is a single, front-loaded sentence with no filler. Every phrase contributes meaning: the action, the target resource, and a critical behavioral distinction.

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 state-mutation tool with three required parameters, a nested object, no output schema, and no annotations, the description is incomplete. It does not define acceptable state values, explain optimistic locking via expectedVersion, clarify idempotencyKey semantics, or describe the response/result of the operation.

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 0%, and the description does not map its prose to the parameters. It hints at possible state values ('pause' and 'close') but does not explain the `id`, `state.state`, `state.expectedVersion`, or `idempotencyKey` fields. The schema's `state.state` is a free-form string with no enum, so the agent gets almost no help constructing valid input.

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 clearly identifies a state-changing action on a research run ('Pause new assignments or close a research run') and adds a key qualifier about preserving earned obligations. It distinguishes the target resource from sibling tools like close_case or close_task by scoping to research runs, though it does not name an alternative directly.

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 implies the tool is used when a research run should be paused or closed, but it gives no explicit guidance about when to choose this over create_research_run, read_research_dashboard, or close_case. There are no stated exclusions, prerequisites, or alternative conditions.

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