configure_watch

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 real behavior: what auto_pause reacts to ('overtemp, confident vision failure'), what vision_sampling actually does per snapshot, and the client capability it requires. It omits persistence semantics (does a call replace or merge existing config?), whether the watch loop restarts, and any permission requirements.

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?

Purpose is front-loaded in five words, then a compact gloss per flag with the higher-risk detail (vision_sampling's sampling requirement) called out inline. Efficient, though the list-style glossing stops short of the interval parameter rather than trimming anything unnecessary.

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?

All parameters are optional and there is no output schema, yet the description never states defaults, whether an omitted flag is preserved or reset, or what watch_interval_sec controls in practice. The prerequisite for vision_sampling is good, but a zero-required-param config tool needs to explain the omission semantics.

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 only 20% (just auto_eject), so the description must compensate for four booleans plus the interval. It meaningfully defines three of them, but auto_eject is left to the schema's terse note and watch_interval_sec (15-600s) is never mentioned at all, leaving a gap the agent must guess about.

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?

'Configure background supervision' gives a specific verb and resource, and the per-flag glosses make clear this tunes the watch loop rather than the printer itself. It is distinguishable from configure_eject/configure_cost by subject matter, though it never names those siblings explicitly.

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 glosses imply when each flag matters (auto_pause on overtemp, vision_sampling for periodic judgement), and it usefully flags the MCP-sampling prerequisite. But there is no explicit when-to-use/when-not guidance, no mention of how this relates to configure_eject (which owns auto_eject) or to queue_dispatch, so routing is left to inference.

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