review_thread

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

With no annotations, the description carries the full burden. It discloses that a separate Claude process is spawned, explains the behavior of both 'auto' and 'inline' modes, mentions the write-origin setting for curator pruning, and describes the return values. However, it does not mention idempotency or consequences of repeated calls on the same thread.

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 concise with two clear paragraphs, and the second paragraph uses a list-like format for parameters. It is front-loaded with the main purpose. Minor improvements could include structuring parameter info more rigidly, but overall it is efficient.

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 covers the core functionality, parameters, modes, and return values. It does not mention prerequisites like thread must be closed or error handling. With an output schema hinted but not shown, the description provides sufficient context for an agent to decide to use the tool.

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 coverage is 0%, so the description must compensate. It explains the 'focus' and 'mode' parameters in detail, listing allowed values and their effects. The 'thread_id' parameter lacks explicit description but is implied by the tool name and description. The default values are documented.

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 clearly states it spawns a background review of a closed thread to extract memory/skills. It provides specific verb ('spawn'), resource ('closed thread'), and detailed purpose, distinguishing it from sibling tools that may also involve review but with different scopes or triggers.

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 for reviewing closed threads and extracting memory/skills, but does not explicitly state when to use this tool versus alternatives like auto_review_trigger or candidate_review_run. No when-not-to-use or exclusion criteria are provided.

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