Run one GraphQL mutation

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds real context beyond them: it injects __typename and a MutationError catch-all to surface HTTP 200 failures that would otherwise look successful, and it states there is no automatic retry, which materially affects agent retry strategy.

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?

Three short, front-loaded sentences with no filler; the operational constraints (single root field, error catch-all, no retry) come first. Slightly telegraphic phrasing like 'explicit confirmation' is only fully resolved by reading the schema.

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 generic mutation executor with no output schema, the description covers the essentials: input shape constraints, failure detection via __typename/MutationError, and retry policy. It stops short of describing what a successful response looks like, which an agent might want given the absence of an output 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?

Schema coverage is 75%, near the high-coverage baseline, and account, confirm and variables are already documented in the schema. The description usefully constrains the required `document` param ('one parsed mutation, one direct root field'), which the schema leaves undescribed, but it adds no detail on the confirm/account relationship beyond what the schema says.

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+resource ('run one parsed GraphQL mutation') and adds structural constraints ('one direct root field and explicit confirmation'), so the agent knows exactly what this tool accepts. It does not explicitly name graphql_query or preview_operation as the counterparts, so sibling differentiation is implied rather than stated.

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?

Encodes one usage precondition ('explicit confirmation'), which implies the agent must confirm before calling. However, it never says when to choose this over graphql_query or preview_operation, nor when-not to use it, leaving routing between the three graphql-related siblings to inference.

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