remind_graphql

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

Beyond the readOnlyHint annotation, the description discloses three non-obvious behaviors: introspection is enabled, mutations are rejected, and unknown fields surface as a 500-backed GRAPHQL_VALIDATION_FAILED rather than a normal field error. The error-shape warning is exactly the kind of operational detail annotations cannot convey.

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 sentences, front-loaded with the core capability, then the introspection affordance, then the write-boundary and error caveat. Every sentence carries a distinct operational fact and none is padding.

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 raw-query escape hatch whose return shape is defined by the caller's own query, the definition covers the constraints an agent needs: read-only scope, introspection availability, the write alternative, and the unusual error semantics. No output schema is required since responses are arbitrary by design.

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% and both parameters (query, variables) are documented in the schema, so baseline 3 applies. The description adds GraphQL syntax examples for the query string, but nothing about how variables bind to the document, so it is largely redundant with the 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?

States a specific verb and resource ('Run an arbitrary READ-ONLY GraphQL query against Remind's API') and immediately differentiates from the typed sibling tools by noting it reaches fields 'the typed tools do not expose'. An agent can distinguish this escape hatch from remind_get_classes, remind_list_chats, etc. without reading any 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?

Explicitly scopes when to use it (introspection-based field discovery) and when not to (mutations are rejected), directing writes to the write tools and noting those preview and confirm. The alternative path is named, not left to inference.

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