update_ticket

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

Annotations provide readOnlyHint=false, openWorldHint=true, destructiveHint=true, which the description fully supports. Beyond that, it discloses the server-side resolution of the assignee to a Zendesk agent, the 400 error for unresolvable emails, the Zendesk auto-close behavior, and that the response echoes applied fields. This far exceeds what the annotations alone convey and adds genuine behavioral context. No contradiction with annotations.

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?

The description is a single dense paragraph of roughly 120 words. Every sentence carries load-bearing information (permissions, exclusions, error behavior, response format), so nothing is wasted. It's somewhat long, but the volume is justified by the role-based permission model and Zendesk integration details. Slightly compact structure but front-loaded with the core purpose.

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 properly explains the return value ('The response echoes the fields that were applied'). It covers the permission model, error cases (400 for unresolvable assignee), enum constraints, auto-close behavior, and the requirement that at least one mutable field be present. For a moderate-complexity mutation tool touching Zendesk, this is 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 coverage is 75% (only `ticketId` lacks a schema description, and it's a simple number). The description adds substantial meaning: `status` semantics are role-restricted with an enum, `assignee` is contextualized as a DoiT-employee email resolved server-side, and `customerContext` explains when it's required vs omitted. This adds deep semantics beyond the bare schema text.

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?

The description opens with the generic framing 'Create and manage support tickets' but then states a precise purpose: 'Partially updates a support request' with the specific fields involved (`status`, `assignee`). It clearly distinguishes from the sibling `create_ticket` and aligns with other ticket tools. The verb+resource+scope is specific and 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?

Usage rules are exceptionally explicit: DoiT employees may set `open`/`pending`/`hold`/`solved` and the assignee, while customers may only set `solved` and may not set an assignee. It explicitly states what is NOT possible (`closed` is not settable via API, auto-closed from `solved`) and the constraint 'At least one mutable field must be present.' This is concrete when/when-not guidance, though it doesn't name alternative tools.

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