incidents

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

No annotations are provided, so description carries the burden. It discloses Relay pagination, common states, and variable structure, which gives a clear behavioral picture. 'List' implies a safe read operation.

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?

Front-loaded with purpose, then provides essential details on pagination, states, and variables. The example is useful but a bit lengthy; still well-organized and each part contributes.

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?

Without an output schema, the description covers the return envelope (edges/pageInfo/totalCount) and mentions filtering and ordering. It could detail node fields, but for a list tool this is adequate and actionable.

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 descriptions are minimal ('GraphQL: String'), offering little meaning. The description compensates by listing variables and providing a concrete example of the incidentFilter structure, adding significant semantic value.

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?

Clearly states the action ('List security incidents') with filtering and ordering capabilities. The scope distinguishes it from singular 'incident' and other incident-related tools.

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?

Implies usage for listing and filtering incidents with pagination. Provides context on common states and example variables, but does not explicitly mention alternatives or when not to use.

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