swsd_create_incident

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

Annotations already indicate a write operation (readOnlyHint=false, idempotentHint=false). The description adds critical behavioral detail: 'WRITE — does not retry on transient failure; the agent should verify with swsd_get_incident before retrying' and notes un-supported custom field types. No contradictions 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?

Concise and well-structured: opens with the core action, then required/recommended fields, followed by behavioral notes (WRITE, retry behavior), then custom field instructions. Every sentence adds information, no redundancy.

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?

Given 9 parameters, no output schema, and the need to guide creation flow, the description covers all key aspects: prerequisites (required fields), error handling (verify before retry), custom field discovery and validation, and unsupported features. It also hints at the output (returned ID) for follow-up calls.

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%, so descriptions already explain most parameters. However, the description adds significant value by highlighting which parameters are strongly recommended, explaining the custom_fields array's validation rules in depth (date format, dropdown values, etc.), and clarifying that it does not support multi_picklist or User types.

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 clearly states 'Create a new SWSD incident' with explicit required and recommended fields. It distinguishes itself by naming follow-up tools (swsd_assign_incident, swsd_add_incident_comment) and contrasting with update/read tools, making its specific role 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 explicit guidance: required `name`, strongly recommended fields, when to use custom fields (after calling swsd_describe_custom_fields), and crucially, what to do on transient failure (verify with swsd_get_incident before retrying). Also clarifies unsupported custom field types (multi_picklist, User) and validates allowed types.

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