Create incident

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the core behavioral burden is covered. The description adds some value by disclosing the return type (parsed Pydantic model) and the failure modes (MissingParameterError, ParameterError on serialization/validation). It does not, however, describe what fields are needed or what a valid payload 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?

The one useful sentence is front-loaded, but the remainder is Sphinx docstring boilerplate (:type, :rtype, repeated :raises ParameterError) that consumes space without informing the agent. The ':param kwargs:' notation does not even match the actual flat parameter schema, adding noise rather than clarity.

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 mutation tool with 15 parameters, no output schema, and no parameter documentation anywhere, the description is inadequate. Annotations cover the safety profile, but an agent still cannot determine what to pass in the data object or how the sysparm_* params behave, leaving a major gap for correct invocation.

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?

There are 15 parameters at 0% schema description coverage, and the description does not compensate. It refers only to generic ':param kwargs:' rather than mapping to the actual named params (data, incident_id, sysparm_view, sysparm_query, etc.). The :raises clause implies 'data' is needed, but the remaining 14 params are entirely undocumented in both the schema and the description.

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 opening line states a specific verb and resource: 'Create a new incident record.' This distinguishes it from sibling creation tools for change requests, problems, and CMDB instances. However, it offers no explicit routing against siblings like servicenow_ingest_incidents or servicenow_add_table_record, so differentiation is implicit only.

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?

The description provides no when-to-use guidance, no prerequisites, and no mention of alternatives. The :raises MissingParameterError line hints that incident 'data' is expected, but this is buried in docstring boilerplate rather than framed as usage guidance.

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