recovery_signals

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

The description discloses a key behavioral trait: it does not return object IDs, messages, paths, or contents, implying a read-only counting operation. This adds transparency beyond the schema. However, it does not describe the output format or any potential side effects, though the absence of annotations raises the bar slightly.

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?

The description is a single concise sentence that is well-structured, front-loaded with the main action, and contains no redundant words or 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?

For a tool with one optional parameter and no output schema, the description covers the core purpose and the main behavioral constraint. It could be more explicit about what 'recovery hints' includes, but the overall information is sufficient for basic selection.

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 schema fully documents the only parameter 'cwd' with a description including that no network access is used. The description adds no additional parameter semantics, but since schema coverage is 100%, the baseline score of 3 is appropriate.

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 uses a specific verb 'Count' and identifies the resource as 'unreachable Git object types and recovery hints', and explicitly states what is excluded (object IDs, messages, paths, contents), which distinguishes it from sibling tools like reflog_signals and stash_signals.

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 implies usage when summary counts of unreachable objects are needed, but it does not explicitly state when to use this tool over alternatives or provide exclusions. No reference to sibling tools is made, though the 'without returning...' clause hints at use cases where detailed data is not required.

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