Build a rescue plan

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

Annotations only declare readOnlyHint and openWorldHint=false, so the description usefully adds that the output is a prescriptive, finding-linked plan with estimated score gains rather than raw analysis. It does not disclose cost, latency, whether it re-scans the site, or any limits on scan_id age, leaving the heavier behavioral burden partly unmet.

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 sentences, front-loaded with the transformation and its outputs, closing with the follow-up loop. Every clause carries information and nothing is padded.

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?

With no output schema, the description does the work of explaining what the caller receives — a prioritised plan with findings, file:line references, and estimated score gain — which is exactly what an agent needs to decide whether the result is usable. Only the ambiguity about how this differs from sibling report/guide tools remains.

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 100% with clear per-parameter docs (keep, lang, scan_id with an example, target_score with a default), so the schema already carries parameter meaning. The description adds no extra syntax or semantics for these parameters, which is the expected baseline.

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 names a specific transformation (scan → prioritised, site-specific plan) and enumerates the concrete artifacts produced (quick clean-ups, copy rewrites, design direction, trust fixes), each tied to findings and file:line locations. This clearly distinguishes it from slop_scan (which produces the input) and the other report/guide siblings.

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?

It states the position in the workflow — turn a scan into a plan, then call slop_scan again to measure — which implies this runs after a scan. However, it gives no guidance on when to prefer this over slop_report, slop_fix, slop_guide, or slop_compare, which is the actual selection problem among eight siblings.

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