create_case

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

With no annotations provided, the description carries the full transparency burden. It discloses a critical behavioral quirk — omitting `state` causes the GreyMatter API to return success=false with no error — and gives concrete guidance to avoid that failure. It doesn't describe success response shape, but the disclosed failure mode is valuable behavioral context beyond the schema.

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?

Every sentence delivers needed information: purpose, the critical state trap, required/optional enums, and a complete example. The example is long but directly usable and not wasteful. The description is front-loaded with purpose before diving into caveats.

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 the opaque input schema (just a GraphQL type name) and no output schema, the description thoroughly equips an agent to invoke the tool correctly. It covers the effectively-required field, enum ranges, and a full example payload. The only minor omission is the `customer_slug` override, but that is already described in the schema.

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?

The top-level schema only says 'GraphQL: CreateCaseInput!' for `input`, giving no information about inner fields. The description compensates fully by explaining that `state` is effectively required, listing allowed values for `type` and `severity`, and providing a complete example variables object. This is far beyond the schema's own semantics.

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 'Create a case' — a specific verb and resource. It clearly distinguishes this from sibling tools like update_case, close_case, and cancel_case, and reinforces the purpose with details about required fields.

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 strong contextual guidance: it explicitly warns that `state` is effectively required despite being schema-optional, and specifies which enum values are valid for `type` and `severity`. It does not explicitly compare against alternatives like update_case, but the usage context is clear enough for an agent to know when to create versus update.

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