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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false). The description adds genuinely new behavioral context: the operator-approval prerequisite, the caveat that a request is "not proof of distress, rest or scheduler control," and the input restriction that no reflection text is accepted. That is useful disclosure beyond the structured fields.

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?

Three tight sentences with no filler, front-loading the purpose before the prerequisites and caveats. Each sentence carries substance, though the second and third shade slightly into abstract cautionary framing rather than actionable guidance.

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?

With nine parameters at 11% schema coverage and no output schema, the description should explain the action modes and the meaning of consent, safe_boundary, resume_confirmed and request_key. It leaves most of these undocumented, so an agent cannot reliably construct calls for actions other than a plain request.

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 only 11% (just account_ref), so the description must carry the load for the other eight parameters, including the action enum, consent, trigger, pause_seconds, safe_boundary and resume_confirmed. It only gestures obliquely at a few of these ("bounded" for pause_seconds, "operator approval" for consent, "resumption" for resume_confirmed) and never maps meaning to any parameter.

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 resource (a bounded pause for one cooperating runtime) and enumerates the operations it fronts (request, inspect, report safe start, report resumption), so an agent can broadly tell what it does. However it does not distinguish this from the sibling eclypse_pause, and cramming five operations into one clause blurs the single purpose.

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?

"Operator approval or a preapproved bounded policy is required before start" gives one real precondition for the start action. But there is no guidance on when to choose request vs read vs list vs resume vs cancel, and no comparison to the sibling eclypse_pause, so usage is only implied.

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