bed_mesh_profile

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false), the description discloses two facts the annotations do not: 'save' mutates printer.cfg and restarts Klipper, and save/remove are two-step operations because they rewrite config. That is exactly the kind of behavioral context that matters. However, it never explains what 'two-step' actually requires — the confirm and confirm_token parameters are left uninterpreted, so an agent still has to guess the confirmation flow.

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?

Two sentences, no padding, and the destructive restart warning is front-loaded inside the action it belongs to. The parenthetical about printer.cfg and Klipper restart is placed exactly where an agent scanning action semantics will need it.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. Still, for a destructive tool that rewrites config and restarts the printer, the description omits the confirmation mechanics, any lease/permission requirements, and what happens if a named profile does not exist. It is adequate but leaves real gaps for a high-risk mutation.

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%, so the description must carry all parameter meaning. It does well on 'action', documenting all four values, but 'name', 'confirm', and 'confirm_token' are never explained beyond a vague 'two-step' aside. The single most important parameter for a destructive flow — confirm_token — is entirely unaddressed.

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 uses a specific verb ('Manage') plus resource ('bed mesh profiles') and then enumerates every action value with its effect: 'load' applies, 'save' persists, 'remove' deletes, 'clear' drops the active mesh. That is far more specific than a bare 'manage' label, and it implicitly separates this from the read-only get_bed_mesh and the calibration sibling. It stops short of naming a sibling outright, which keeps it from a 5.

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?

Usage context is clear for each action, and there is a genuine warning about side effects ('this writes printer.cfg and RESTARTS Klipper'). The schema has zero enums, so the description is doing real work by spelling out the four valid action values. What is missing is exclusions or prerequisites, e.g. that 'load'/'remove' require a name, or when to prefer bed_mesh_calibrate over saving the current mesh.

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