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

Annotations only supply destructiveHint=true; the description adds the crucial undisclosed behaviors — that is_note=false triggers an email to the requester and 'cannot be unsent', and it names the underlying endpoint. This is real content beyond structured fields.

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?

Two tight sentences with no filler; the note-vs-reply distinction and its consequence are front-loaded, and the endpoint is appended as low-priority detail.

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 4-parameter mutation tool with full schema coverage, no output schema, and only a destructiveHint annotation, the description covers everything an agent needs: the mutation target, the branching mode, and the irreversible side effect.

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 every parameter already carries a description, so the baseline is 3. The description restates is_note semantics (already in the schema) and says nothing about format or ticket_id beyond what the schema provides.

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 (add) and resource (message on a ticket) with an explicit actor ('as the key's agent'), and splits the two modes by is_note. It is clearly distinguishable from the sibling deskpro_list_ticket_messages, which only reads messages.

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 clear conditional guidance for the core decision: is_note=true for internal notes, is_note=false for a public reply, plus the consequence that a reply is emailed and irreversible. It does not, however, contrast this tool against siblings like deskpro_update_ticket, so no alternative-routing guidance is offered.

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