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

Annotations already declare readOnly=false, destructive=false, idempotent=true, openWorld=false, so the safety profile is covered. The description adds value beyond them with "Nothing is sent" (no notification goes to the worker) and the retry protocol of reusing the same idempotency_key. Neither the scope of the deletion (one worker, one date only) nor the response shape is spelled out further.

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?

Four short sentences with the core action first, then the scope, the sibling pointer, the side-effect note, and the retry rule. No filler, and the UI comparison ("as Clear on the staff calendar does") earns its place by grounding the semantics.

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?

No output schema exists, so the description should say what a successful call returns or how to tell "no override existed" apart from success — it does not. The cleaner_name format and any permission requirements are also unaddressed. For a three-required-parameter mutation this is adequate but leaves real gaps.

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 33%, so the description must carry more weight than it does. It does clarify the date format (redundant with the pattern) and restates idempotency-key reuse, but never explains what cleaner_name expects — an exact name string versus an identifier — which is the parameter most likely to be passed wrongly. Baseline 3 for the partial compensation.

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?

Names a specific verb and resource ("Clears one field worker's schedule change on a date") plus the effect ("normal weekly hours apply again") and anchors it to a familiar UI action. It explicitly distinguishes itself from set_staff_availability, so an agent can route between the pair without opening either schema.

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 line "To set a change, use set_staff_availability" gives an explicit alternative and the condition that selects it, and the retry instruction tells the agent what to do on failure. It lacks an explicit when-not-to-use case (e.g. no override exists, past dates), which is why it falls short of a 5.

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