Report whether a recalled fix worked

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

It discloses important behavior beyond annotations: the tool does not create a verified vote and is retained only for compatibility. However, with no read-only or idempotency indicators supported by a clear side-effect model, it does not explain exactly what state it writes or what the caller should expect after invoking it. This is a meaningful but incomplete disclosure.

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 sentences carry the full message with no filler. The legacy caveat and the alternative tools are front-loaded, making the key guidance immediately visible.

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?

It gives the essential context for an agent deciding whether this tool is appropriate: legacy compatibility only, with begin_attempt and feedback as preferred replacements. It lacks information about return format or write outcome, and since there is no output schema and only weak annotations, a tool-calling agent needing to use it directly may still be undersupplied.

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 input schema already describes `id` and `note`, but the description adds no additional meaning to any of the three parameters. With 67% schema coverage and `worked` undetailed, the description leaves room to clarify parameter semantics but does not. It relies entirely on the schema and title for parameter understanding.

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 title and tool name clearly state the purpose: report whether a recalled fix worked. The description adds that this reporting is legacy-only and explicitly contrasts it with creating a verified vote or raising verified reliability, which separates it from begin_attempt and feedback. However, the description mostly says what the tool is not rather than providing a direct verb+resource purpose.

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 explicitly says to use alternatives: 'New clients should use begin_attempt and feedback.' It also explains retention is for compatibility, signaling this tool is only for existing legacy clients. This leaves no ambiguity about when and when not to use it.

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