fleet_pause

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

With no annotations, the description carries the full burden and does disclose a critical non-obvious trait: the first call mutates nothing and only reports intended actions, and execution requires echoing back the `actions_digest`. That is real behavioral value beyond what any structured field conveys. It still omits what 'gracefully' means in practice (e.g., whether a running print finishes its current layer), whether auth/tier checks fail the call, and how partial fleet failures are reported.

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 purpose is correctly front-loaded in the first clause. But the middle section is upsell material — tier limits, 'grow to 50', and an upgrade URL literally stamped with a tracking parameter — that consumes space without helping the agent call the tool, and the final sentence is a long run-on that buries the two-phase protocol.

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?

There is no output schema and no annotations, so the description must cover both behavior and return semantics; it covers the two-phase protocol but not what the first-call payload looks like (shape of actions_digest, what actions are listed) or which printers are targeted by default. For a fleet-wide mutating tool with zero annotations, this leaves meaningful gaps around targeting and failure behavior.

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 coverage is 67% and two of three parameters have placeholder-only descriptions ('Default: true.', 'Default: ""'). The description does clarify `run_actions` semantics by tying it to the actions_digest value returned by the first call, which the schema does not say. It adds nothing about `printer_names` (can it be omitted to mean all printers?) or why `keep_temps` matters when pausing.

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 gives a specific verb and resource with explicit scope: 'Pause printing across the whole fleet.' The word 'fleet' implicitly separates it from the single-printer `pause_print` sibling, but no sibling is named and 'gracefully' is left undefined, so an agent must still infer the distinction.

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 explains the two-step invocation pattern (dry-run call, then re-call with `run_actions` set to the returned digest), which is genuine usage guidance. However, it never states when to prefer this over `pause_print` or how it relates to `fleet_resume`/`fleet_cancel`, and the only exclusions are commercial tier gates rather than operational conditions.

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