yc_commit_mutation

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

Annotations already flag the call as destructive, non-read-only and open-world, but the description adds what those flags cannot: a successful GraphQL envelope is not proof of success, and rejected, unverified or uncertain outcomes are errors carrying durable receipts. That is exactly the failure-mode context an agent needs before firing a destructive mutation, plus a read-back and no-blind-retry directive.

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 action and its binding, then the error semantics, then the operational imperative. No filler and no repetition of schema or annotation content.

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?

Output schema exists, so return shape need not be explained, and the description covers the high-risk behavior: digest binding, error taxonomy, durable receipts, read-back. What's missing is whether the receipt is consumed on success, whether a failed or uncertain outcome can leave partial state, and where the receiptId is obtained.

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 0%, so both parameters are bare format-constrained strings, and the description is the only source of meaning: it ties 'exact digest' to confirmDigest and 'previously reviewed mutation' to receiptId. It does not say where the receipt comes from, that the digest must match the reviewed payload byte-for-byte, or how mismatch errors surface, so it only partly compensates for the coverage gap.

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?

"Execute the previously reviewed mutation once, bound to its exact digest and authenticated target" gives a specific verb (execute), a specific resource (a previously reviewed mutation), and its binding constraints. It clearly distinguishes this from read-only query siblings and implies a prior prepare/review step, though it never names yc_prepare_mutation or yc_mutation_receipts explicitly.

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?

"Previously reviewed" establishes the precondition, and "never retry blindly" plus "Read back all changes" gives post-call guidance an agent would otherwise get wrong. No alternative tool is named and no explicit when-not-to-use condition is stated, so it stops short of routing guidance.

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