yc_prepare_mutation

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

Adds real behavior beyond the annotations: it performs no network contact with YC, so no server state changes even though readOnlyHint is false; it requires a mutation-enabling flag and transport policy switch; and it requires a UUID idempotency key per logical change. That is exactly the kind of nuance annotations cannot convey. What it doesn't cover is what happens when validation fails or whether preview output includes the resolved target details.

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 short, front-loaded sentences with no filler; the no-network guarantee leads, followed by the key requirement, followed by the review instruction. The closing fragment 'Review before commit' is terse but readable. Nothing here 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?

An output schema exists, so return values need not be described, and the description covers the safety-relevant facts (no contact, flag prerequisites, idempotency). For a four-parameter mutation-preview tool that is nearly complete. The gap is guidance on the relationship between the idempotency key's preview and commit lifetimes, and on error handling.

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?

With 0% schema description coverage, the description must compensate and only partly does. It explains idempotencyKey well (UUID, bound to 'this logical change'), which matters because the same key presumably needs to be reused at commit time. But query, operationName and variables are only loosely gestured at ('the exact mutation, variables, fields'), with no format or validation guidance for the required operationName pattern.

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: 'Preview the exact mutation, variables, fields and authenticated target' — a dry-run of a GraphQL mutation. The phrase 'without contacting YC' fixes the scope sharply, and 'Review before commit' implicitly separates it from the commit sibling. It stops short of naming an alternative, but the resource and verb are unambiguous.

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 usage context: preview the change, then review before committing, with the prerequisites '--allow-mutations and any transport policy switch' spelled out. What's missing is an explicit pointer to yc_commit_mutation as the next step in the workflow, leaving the agent to infer the pairing from the phrase 'before commit'.

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