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

Annotations only supply destructiveHint=true, so the description must carry the load, and it does: it marks the call as a WRITE, discloses the real side effect (email is actually sent to the customer on MAIL, suppressed on NOTE), and names the underlying endpoint. It does not mention auth requirements or what a failed/rejected send looks like.

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 the WRITE marker front-loaded and the highest-risk semantics (email vs no email) stated before the housekeeping. The trailing raw endpoint 'Kayako: POST /api/v1/cases.json' is low-value filler, but overall the text is dense and earns its length.

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 15-param write tool with no output schema and a nested field_values object, the description covers the creation flow, the channel fork, and prerequisite id lookups. It stops short of describing what is returned or the form_id/custom-field interaction, so an agent still has gaps.

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 60% across 15 params. The description adds genuine meaning for channel/channel_id behavior and for where status_id, priority_id and type_id values come from, but leaves form_id, field_values, assigned_agent_id/team_id, tags, cc, and html entirely to sparse schema text. Partial compensation only.

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+resource ('WRITE: open a new case (conversation) for a requester'), defines the domain term 'case' as a conversation, and is clearly distinct from sibling kayako_reply_to_case / kayako_update_case which operate on existing cases. An agent can select it without opening the schema.

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 concrete routing guidance: MAIL emails the customer from the channel_id mailbox, NOTE creates an internal note and emails nobody, and explicitly points to kayako_list_channels and kayako_list_case_options for id lookups. It lacks an explicit 'not for existing cases, use reply_to_case' statement, so it stops just short of full alternative coverage.

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