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

Annotations only provide destructiveHint=true, so the description carries most of the burden and does well: 'Sends nothing to the customer' is a real behavioral disclosure an agent cannot infer, and the explicit exclusion of trashing clarifies blast radius. It also pins the underlying call (PUT /api/v1/cases/{id}.json). It does not say whether omitted fields are preserved or what happens on failure.

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?

One tight, front-loaded paragraph with the 'WRITE:' prefix leading immediately into the effect. Nearly every clause earns its place (field list, tag routing, trashing exclusion, endpoint). The endpoint string is the one mildly expendable element.

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 12-parameter mutation tool with no output schema and minimal annotation coverage, the description covers the mutable surface, the tag semantics, and the deliberately excluded destructive operation. Missing only edge behavior: partial-update semantics for omitted fields and auth/permission expectations.

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?

With only 25% schema description coverage across 12 parameters, the description is the primary documentation and it names nearly every updatable field, including the assignee split (team/agent) and custom fields. It adds the crucial set-vs-append semantics for tags that the schema only partially conveys. It could still clarify how custom-field multi-select CSV behavior maps to the operation.

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 an explicit verb+resource ('WRITE: change a case's...') and enumerates exactly which attributes are mutable (subject, requester, assignee, status, priority, type, brand, form, tags, custom fields). It also names the sibling it is not (kayako_add_case_tags) and notes that trashing is deliberately excluded, so an agent can pick it apart from the other case tools at a glance.

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 a clear conditional: use this tool to set the tag list, use kayako_add_case_tags to append, which is exactly the distinction an agent needs. It also states a when-not (no trashing exposed). It stops short of spelling out prerequisites such as required permissions or which case states can be edited.

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