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

Beyond the destructiveHint=true annotation, the description discloses the actual destructive mechanism ('Arrays replace the full saved array: read and preserve entries the user did not ask to remove') and reassures on scope ('existing meetings do not move', 'Only supplied fields change'). It explains what is destroyed, what is untouched, and where the change propagates (all booking pages, meeting searches, workspaces).

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 purpose, then destructive-array warning, then alternative, then when-to-use and an example. Every sentence is load-bearing except for mild repetition between the opening field list, the 'When to use' line listing the same fields, and the near-duplicate scope statements about workspaces/booking pages.

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?

With an output schema present, annotations covering the safety profile, and 100% schema description coverage, the only thing an agent must know is the array-replacement hazard and the read-preserve workflow — both are stated explicitly. Nothing needed to invoke this 10-parameter patch tool correctly is missing.

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 semantics the schema does not carry: 'Hours are whole hours in the saved IANA timezone' and the blanket 'Only supplied fields change / arrays replace the full saved array' rule that generalizes the per-field replacement notes. It does not add format detail for expected_updated_at beyond what the schema already says.

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 and resource ('Change your saved scheduling hours, timezone, workdays, recurring blackouts, buffers or minimum notice') and enumerates the mutable fields. It also distinguishes itself from siblings by name ('For a one-off search constraint use find_times instead') and from get_scheduling_settings via the read-first workflow.

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?

Explicit 'When to use' section states the trigger condition ('Patch your saved ... after reading current settings'), names the alternative for a different need (find_times), and the schema documents the expected_updated_at conflict path. Nothing about when/when-not 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.