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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: it targets the edge endpoint, notes each project has its own generated schema, and discloses the `root(context: ...)` query root field needed to form a valid query. No auth/rate-limit detail, but solid for a read-only tool.

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 tight sentences, front-loaded with the core action, then the escape-hatch rationale, then the critical root-field detail. No filler; every sentence carries weight.

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 GraphQL escape hatch with no output schema, the description is nearly complete: it explains the endpoint, the per-project schema constraint, and the root field. Minor gaps remain around return shape and error behavior, but the agent has enough to invoke it correctly.

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%, so the schema documents both `query` and `variables` with examples. The description still adds meaning by revealing the mandatory `root(context: ...)` root field, which is essential for constructing a working query and isn't captured elsewhere.

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) and resource (arbitrary GraphQL query against the Hypertune edge endpoint) and positions itself as the 'power-user escape hatch' relative to the convenience tools. An agent can distinguish this from hypertune_evaluate or hypertune_list_flags without opening either 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?

Clearly conveys when to reach for it: cases the convenience tools can't express, such as arbitrary flag shapes, nested selections, inline enum literals, or variables. It doesn't name the sibling tools or state explicit exclusions (when NOT to use it), but the routing condition is unambiguous.

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