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

Annotations declare readOnlyHint=true, and the description goes beyond that with a real behavioral constraint (mutations rejected), an auth requirement ('matching read scope(s) on your token'), and the target endpoint. It does not mention rate limits, query depth/complexity limits, or the response shape, so it stops short of the top score.

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 the escape-hatch framing and tightly written; four sentences each carry information (scope, endpoint, rejection rule, family routing, auth). Slightly dense but no filler.

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 GraphQL passthrough with no output schema, the description covers purpose, restrictions, and auth scope adequately; the agent already knows a GraphQL response shape. Minor gap: no mention of complexity/pagination limits for arbitrary queries.

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 description coverage is 100% with only two parameters, so the schema already documents 'query' and 'variables' fully. The description adds marginal value by noting variables are optional, but supplies no format or syntax guidance beyond the schema. Baseline 3 applies.

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 ('run an arbitrary Parabol GraphQL QUERY') plus the exact endpoint, and explicitly distinguishes itself from siblings: it is the read-only escape hatch while 'parabol_graphql' and the dedicated write tools handle mutations. An agent can route correctly without opening the schema.

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 both when-to-use ('for fields not covered by the curated read tools') and when-not ('Mutations are REJECTED'), and names the alternative tools to use in the rejected case. This is explicit routing guidance, not inference.

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