entain_graphql_call

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

No annotations exist, so description carries full burden. It describes server-side hash management, self-healing behavior, error handling, and variable format conventions. It does not specify whether operations include mutations, but the phrase 'Call any operations' implies both queries and mutations.

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?

Well-structured with front-loaded purpose. Each sentence adds value (endpoint, self-healing, variable types). Slightly lengthy due to technical details, but no fluff.

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?

Given no output schema (only 'Returns JSON object'), description covers error handling, variable types, and a reference for operations. Could mention that return shape varies by operation, but referencing the op list suffices.

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 0%, so description compensates fully. It explains 'operation' as a name, 'variables' as an object, and provides critical context about GraphQL ID formatting (type-prefixed vs bare UUID). Also references entain://graphql/operations for full list, adding immense value beyond schema.

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?

The description explicitly states it calls any of Entain's 127 persisted GraphQL operations by name and variables, specifying the endpoint (api.ladbrokes.com.au/gql/router). It clearly distinguishes from sibling tools that are more specific (e.g., entain_cms_entries, entain_racing_racecard) by being a general-purpose GraphQL caller.

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 guidance on when to use (persisted GraphQL operations), includes error handling (self-healing APQ cache eviction) and a fallback command (refresh-hashes). Also gives variable type hints (ID! vs UUID!). Lacks explicit 'when not to use' but context with sibling tools helps.

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