remind_graphql

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

With annotations covering readOnlyHint and openWorldHint, the description still adds substantial value beyond them: mutation rejection policy, introspection availability, the specific 500-backed GRAPHQL_VALIDATION_FAILED error shape for unknown fields, and a prompt-injection warning that returned text is third-party and untrusted. These are exactly the operational traits annotations cannot carry.

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-loads the core action, then layers example queries, the mutation restriction with the redirect to write tools, the error-format gotcha, and the security caveat. Every sentence carries distinct, non-redundant information; length is justified by the tool's abstraction level.

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 with no output schema, the description covers invocation semantics, permitted operations, error behavior, and safety handling of returned data. Nothing an agent needs to call it correctly is missing.

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 100%, so query and variables are already documented, giving a baseline of 3. The description goes further by supplying concrete introspection query examples (`{ __schema { ... } }`, `{ __type(name:"Class") { fields { name } } }`) that illustrate valid query syntax, slightly exceeding what the schema provides.

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 (Run), resource (arbitrary READ-ONLY GraphQL query), and target (Remind's API), and explicitly contrasts with 'the typed tools' in the sibling set. An agent can immediately distinguish this from remind_list_entities, remind_get_classes, etc.

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 tells when to reach for this tool (discovering fields the typed tools do not expose, via introspection examples) and when not to (mutations are rejected — use the write tools instead, which preview and confirm). Nothing is left to inference.

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