loop_stop

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

Annotations already declare this is a mutating, non-idempotent, closed-world operation, so safety expectations are partly covered. The description adds the verdict/reason gating rules, but says nothing about the resulting loop state, whether a stop can be undone, or what a failed precondition does.

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 short sentences, front-loaded with the action and followed immediately by the hard constraints. Only minor loss is the slightly compressed phrasing of the non-success-reason rule.

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 mutating tool with no output schema, the description covers the essential call conditions. The main gaps are the undocumented cwd parameter and the absence of any statement about what the tool returns or the loop's resulting state.

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 83% and the schema already documents id, reason, success, authority_file, and workspace_root. The description's success/verdict and reason framing largely restates the schema text rather than adding new semantics, so the baseline of 3 applies; cwd remains undocumented in both places.

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?

Names a specific verb and resource ('Stop a loop contract'), which distinguishes it cleanly from siblings like loop_start, loop_status, and loop_record_attempt. It stops short of explicitly naming the siblings it is not, so it lands just under a 5.

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?

Preconditions are stated (success=true needs a passing verdict; a non-success stop needs a reason), which implies when the tool is applicable. However, there is no explicit guidance on when to stop versus continuing via loop_record_attempt, or what to do if the preconditions are unmet.

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