Manage Model Check

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

With no annotations, the description carries the full burden and discharges it: it declares the tool mutating, states pause idempotency, discloses the side effect that work already run is charged, and specifies that refusals return as data (HTTP 409 with codes like not_running, pause_in_progress, not_paused, pause_first) rather than as exceptions. It also describes the intermediate 'pausing' state and where resume re-enters.

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?

One lead sentence establishes verb, resource, and mutating nature, then three parallel per-action bullets each ending in the exact return shape, followed by the refusal-code list. It is dense but every clause carries operational information and nothing is repeated.

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 three-parameter mutation tool with no annotations, the description covers actions, state transitions, preconditions, return payloads, and failure codes. Its one shortfall is that it restates return values that the output schema already provides, and it says nothing about permissions or how to obtain model_id.

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 67% (server_version is undocumented), and the description more than compensates for the action parameter by defining each enum value's effect, timing, and result payload, which the bare enum cannot convey. model_id is left to the schema, and server_version remains unexplained in both places.

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 opening sentence names a specific verb set (pause/resume/discard) against a specific resource (a model's live model check) and flags the operation as mutating. It is clearly separable from read siblings like get_model_check and create-side siblings like request_model_check without opening any schema.

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?

Each action's precondition is spelled out (discard refused while running until paused, resume only after status reads 'paused', pause is idempotent), which is real when-to-use guidance. It stops short of routing the agent to alternatives such as get_model_check for inspecting state or request_model_check for starting a check, so it is clear context without explicit sibling exclusions.

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