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

Goes well beyond the annotations (readOnly=false, destructive=false, openWorld=true) by disclosing that the record is retained and never deleted, that cancelling may hide the appointment from calendar filters, and that notify reaches the client and/or cleaner as an external side effect. The confirmation policy and auth requirement add further behavioral context an agent needs before invoking.

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?

Purpose and non-deletion guarantee are front-loaded. It is slightly bloated with process/policy sentences (confirmation toggling, API key) that are useful but not strictly descriptive of the tool, keeping it just under the top tier.

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 no output schema, the description still conveys the resulting state (Cancelled), the side effect of notifications, filter-visibility impact, confirmation policy, and auth needs. It stops short of describing error/failure behavior, but covers everything needed to invoke the tool correctly.

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% and the enum already documents none/client/cleaner/both and the default. The description restates the choices and adds only marginal framing ('the same choices ZenMaid offers when you cancel'), so the schema does the heavy lifting and the baseline 3 applies.

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 and resource ('Set an appointment to Cancelled') and immediately clarifies scope ('keeps the record; it never deletes'), which distinguishes it from any delete-style operation. Against siblings like reschedule_appointment and get_appointment the intent is unambiguous.

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?

Provides operational context: it reaches other people so the user must confirm before each call, confirmation can be disabled per-tool, and a Cotlet API key with app access is required. It does not name an explicit alternative or exclusion case, so it falls short of the top tier but the usage conditions are clear.

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