amend_candidate

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

Annotations only say the operation is not read-only, not idempotent, and not destructive. The description adds that the patch is a partial replacement ('leaves the rest alone') and that nothing is committed, which is critical side-effect information beyond the annotations.

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 sentences with the purpose front-loaded in the first sentence. The second and third sentences add essential behavioral nuance without filler.

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?

The description captures the key invocation decisions: staged vs committed, partial update, no commit side effect, and revised batch return (output schema covers return shape). The optional expected_batch_digest remains undefined, but the core workflow is well specified.

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?

The description explains patch semantics (replaces named fields, leaves the rest alone), which is valuable because the schema has no descriptions and patch is an open object. batch_id and candidate_id are self-evident, but expected_batch_digest is not explained, leaving a gap given 0% schema description coverage.

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?

The opening sentence names a specific action ('Correct one staged candidate'), the target resource (a candidate within a staged batch), and the timing ('before it is committed'). It also states the return value ('returning the revised batch'), which distinguishes it from commit/withdraw siblings.

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?

The description makes the pre-commit context explicit and adds that confirming an amendment is not acceptance of the batch, preventing use on committed records. It does not name sibling alternatives explicitly, but the staged/committed contrast gives clear context for when this tool applies.

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