Start cleaning

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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower. The description usefully discloses the return payload ('the rooms accepted and the robot's activity a few seconds later'), which matters because there is no output schema. It does not warn that repeat invocation is non-idempotent or what happens if a clean is already running.

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?

Front-loads the action, then walks parameters in a compact per-parameter format, closing with the return behavior. Every sentence carries operational information; nothing is restated from the schema for its own sake.

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 5-parameter, zero-required mutation tool with no output schema, the description covers all parameters, the selection heuristics, and the response shape. The remaining ambiguity (precedence of rooms vs. whole_floor, behavior when a job is already active) is minor but real.

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 100%, so the baseline is 3, but the description adds genuine interpretation the schema lacks: mapping user phrasing ('hoover', 'sweep', 'clean') onto the mode enum, and defaulting coverage to 'standard' unless a quick or thorough pass is requested. The only untouched edge case is what happens when both 'rooms' and 'whole_floor' are supplied, or when neither is.

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?

Opens with a specific verb+resource ('Start the robot cleaning now') and is immediately distinguishable from siblings like matic_pause, matic_resume, and matic_stop, which handle the opposite direction. The scope (rooms vs. whole_floor) is stated in the same breath.

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?

Gives concrete when-to-use rules for each parameter: choose 'rooms' or 'whole_floor', map the user's verb to 'mode', default to 'standard' coverage unless they ask for quick/heavy_duty, and set 'ordered' only for sequential requests. It stops short of naming sibling alternatives (e.g. use matic_resume to continue a paused job rather than starting a new one), so no explicit exclusion is provided.

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