loop_record

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

With no annotations provided, the description must disclose behavioral traits. It explains the revert behavior on 'worse'/'same,' the requirement for graph with 'better,' and the role of score. It also mentions passing outputs for loop_report. However, it does not explicitly describe side effects or error handling, but the key behaviors are covered.

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 somewhat lengthy but well-structured, with bullet points for parameters and clear explanations. It front-loads the purpose. Minor redundancy (e.g., 'Never build on a regression' is reiterated) could be trimmed, 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?

Given the complexity of the tool (7 parameters, loop context) and the presence of an output schema, the description covers the essential aspects: input parameter behavior, decision logic, and the revert mechanism. It does not detail return format, but the output schema likely handles that. The description is sufficient for an agent to use the tool correctly.

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 the description must add meaning for each parameter. It explains 'change' as the modification made, 'outcome' as verdict vs best-so-far, 'graph' as required when outcome is 'better,' 'score' as an objective measure for gates, 'outputs' as files for loop_report, and 'note' and 'run_id' implicitly. This provides significant value beyond the schema.

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's purpose: 'Record a pass and apply the ratchet (loop step 5: DECIDE).' It specifies the verb 'Record a pass and apply the ratchet' and the resource 'loop step 5.' The purpose is distinct from sibling tools like loop_start, loop_best, loop_finish, etc.

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 provides explicit guidance on when and how to use the tool. It explains that on 'worse' or 'same' outcomes, the best graph is returned and a different change should be tried. It also notes that graph is required when outcome is 'better,' and explains the role of score in decision-making. This distinguishes usage from alternatives.

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