Run a read-only GraphQL query

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false; the description reinforces this with "never a mutation", which is the key safety signal for a free-form query tool. It adds real context beyond the annotations (raw unshaped return data, the wave://schema resource, pagination requirement, worked example), but says nothing about query size limits, depth/complexity caps, or error behavior when a query is malformed.

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 decision-relevant framing, then constraints, then schema pointer and example — a sensible ordering with no filler sentences. The opening clause is slightly convoluted ("reads the other tools do not shape the way you need"), but every sentence carries usable information.

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 two-parameter escape hatch with no output schema, the description covers what an agent needs: read-only scope, what comes back (raw data), where the API schema lives, and a concrete call shape. Missing only operational guardrails such as the query length limit and failure modes, which is why it is not a 5.

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 50%: only `query` is documented in the schema, and `variables` has no description at all. The description compensates meaningfully by showing a parameterized query document (`query($id: ID!){...}`), which implies how variables bind, and by pointing to wave://schema for field selection. It still omits the 20000-character cap on `query` and any statement about how `variables` is passed.

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 one GraphQL query ... against Wave's public API") plus the explicit scope boundary "never a mutation". The framing as an "escape hatch for reads the other tools do not shape" immediately distinguishes it from the ~70 shape-specific sibling tools (wave_list_customers, wave_get_invoice, 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?

Gives a clear selection rule: use this only when the purpose-built tools do not shape reads the way you need, and never for mutations. It also supplies two mandatory invocation practices (select only needed fields; always pass page/pageSize on connections) that an agent would otherwise get wrong.

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