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

Annotations already mark it read-only/idempotent/non-destructive, and the description adds substantial behavioral context: it requires the caller's own Bearer token, demands exact camelCase schema names, explains the exact failure mode for unknown fields, and recommends introspection before guessing. There is no contradiction with the 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?

The description is front-loaded with the main action, then each subsequent sentence adds a distinct operational constraint or remedy. Nothing is redundant or decorative.

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 an arbitrary GraphQL passthrough with no output schema, the description covers endpoint, authentication, schema matching, failure behavior, and introspection strategy. It also includes worked examples that show the required query and variable shapes, so an agent has enough to invoke it correctly.

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 only 33%, but the description compensates by explaining that 'query' is arbitrary GraphQL, must match the STRATZ schema exactly, and fails with 'Cannot query field' otherwise, while listing examples with variables. The required `_apiKey` parameter is already well documented in the schema, and the `variables` parameter is covered by the example and the phrase 'with optional variables.'

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?

States a specific verb and resource: 'Send an arbitrary GraphQL query ... to the STRATZ API at api.stratz.com/graphql.' It also establishes the tool's scope as a catch-all, 'Use when no named tool covers the data you need,' which differentiates it from the many named siblings.

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 an explicit selection condition: only use when no named tool covers the needed data. This not only tells when to use it but implicitly when not to use it, so an agent can route around sibling tools without further inference.

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