entain_graphql_call

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantive non-obvious behavior: server-side hash management, automatic self-healing of PERSISTED_QUERY_NOT_FOUND by re-POSTing the stored document, the refresh-hashes fallback, and exact GraphQL ID format rules (ID! vs UUID!). It also discloses optional auth behavior. No contradiction with 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?

Dense but well-organized: primary action first, then error recovery, ID semantics, resource pointer, return type, and auth. The line-separated sections and lack of fluff make it easy to scan; every sentence earns its place.

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 raw-GraphQL tool with no output schema, it covers the endpoint, allowed operations source, error behavior, ID formatting, return type, and auth requirements. Operation-specific outputs are delegated to the catalogue resource, which is appropriate given the 127 possible operations.

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 input schema already describes both operation and variables with 100% coverage, so the baseline is 3. The description adds real parameter-level value by explaining type-prefixed vs bare UUID variable expectations and directing the agent to the catalogue resource for per-operation variable signatures.

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 action: 'Call any of Entain's 127 persisted GraphQL operations' against a named endpoint by name + variables. Unambiguously identifies itself as the generic persisted-query dispatcher for Entain and is distinct from the convenience entain_* tools in the sibling list.

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?

Provides clear usage context: invoke by operation name when you need to run one of the persisted GraphQL operations, and consult entain://graphql/operations for the operation list and variable signatures. It also gives a concrete recovery command for APQ-cache failures, though it does not explicitly name alternative tools or when-not-to-use conditions.

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