loop_ledger

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

No annotations are provided, so the description carries the full burden. It describes the tool as read-only ('append-only', 'read it') and discloses the content: what changed, what it did. It also explains behavioral context (recover thread, avoid retries, best pass). This provides sufficient transparency for an agent.

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 (three sentences) and front-loaded with the core purpose. Each sentence adds value: stating it is append-only, describing its contents, and listing use cases. There is no wasted text, though the parameter is entirely unaddressed.

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?

Given the tool's simplicity (one required parameter) and the presence of an output schema (documenting return values), the description adequately covers purpose and usage context. However, the lack of parameter explanation is a notable gap. The description would be complete if it briefly mentioned that run_id identifies the loop session.

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 only parameter, run_id, has no schema description (0% coverage) and the tool description does not explain what run_id represents or how to obtain it. The description focuses on the tool's output and usage context, not the input parameter. This leaves the agent without guidance on what value to provide.

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 the tool is an append-only loop log that records each pass, what changed, and what it did. It specifies the purpose: read after context compaction to recover thread, avoid retrying dead ends, determine best pass, and provide user sign-off. This distinguishes it from sibling tools like loop_record (which likely records) and loop_report (which likely summarizes).

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 states when to use the tool: 'Read it after a context compaction to recover the thread' and 'hand to user at sign-off'. It implies it is for reading only, but does not explicitly mention when not to use it or alternatives. The purpose is clear enough that usage context is well-understood.

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