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

The annotations already cover the safety profile (idempotent, non-read-only, non-destructive, closed-world), lowering the bar. The description adds genuine context: 'Nothing is sent' reassures no message goes to the cleaner, and it explains that add/link actions attach their past jobs, plus a retry rule for idempotency_key. It doesn't describe the response or what happens when a name matches ambiguously, leaving some behavioral gaps.

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-loaded with the verb and purpose, then compact action definitions and the retry note. The dense parenthetical enumeration is packed but each clause carries information; no filler sentences.

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 four-parameter mutation with no output schema, the description covers the actions, side effects on past jobs, the 'nothing is sent' guarantee, and retry semantics. The main remaining gap is the conditional requirement of staffId and any indication of the return shape, so it isn't fully complete.

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 25% (only idempotency_key is documented), so the description must compensate. It does explain the three action enum values and implies staffId is needed for the 'link' case, but never states that staffId is conditionally required only when action=link, nor clarifies the 'name' parameter's role beyond 'one cleaner name'.

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?

States a specific verb ('Sorts') and resource ('one cleaner name found on bookings') and names the concrete workflow ('Review your cleaner roster'). An agent can tell this is a single-name roster resolution step, distinct from multi-item siblings like add_staff_member. It stops short of explicitly naming an alternative or contrasting tool.

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 gives clear context for when to call it — while working through the Review your cleaner roster step — and spells out the three action intents so the agent knows which branch applies. It lacks explicit when-not conditions or a named alternative tool, which keeps it below a 5.

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