save_correction

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose a real side effect beyond parameter passing, namely that the segment is marked as corrected, which is valuable. It is silent on whether the change is reversible, whether permissions or sync are required, and what happens if the segment was already corrected.

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?

Two short sentences with zero padding: the action comes first, followed by the guardrail. Every clause earns its place and nothing is buried.

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 mutation with no annotations and no output schema, the description covers the core action and the key state change. It leaves gaps about the response, error behavior, and the handling of already-corrected or invalid segments, which matter for a write tool with zero annotation coverage.

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 rely on their names alone plus whatever the prose implies. The description reinforces that segment_id selects 某一段 and that corrected_text is the post-correction text. It adds no format, length, or replacement semantics, such as whether the text fully replaces the original.

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 description states a specific verb and resource: write the corrected text back to a segment and mark it as corrected. This pairs a mutation with a status change, which clearly distinguishes it from read-only siblings such as get_transcript or pending_corrections. It does not name any sibling, so it stops short of full differentiation.

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 second sentence gives an explicit scope restriction: only write text that fixes recognition errors, and do not rewrite content. That is a genuine when-not condition that constrains use. No alternative tool is named, so an agent must infer that correction_guide handles rewrites or guidance.

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