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

Goes well beyond the annotations (idempotent, non-destructive, non-read-only) by disclosing the ranking-signal side effect, the persistence of a skip's down-ranking until undone, the non-cancellation of an in-flight vacancy analysis, the reversible/instant/no-quota nature, and the 'not_found' error condition. Rich behavioral context that the structured fields cannot convey.

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?

Front-loaded with the core action ('Undo a verdict on a radar match'), then layered with edge cases and constraints. Every sentence adds operational value, though the density is near the upper limit and could be trimmed slightly.

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 an output schema present, return values need no explanation, yet the description still surfaces the key 'not_found' case. It covers behavior, side effects, edge cases, parameter source and reversibility, leaving no meaningful gap for a mutation tool of this complexity.

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?

With stated schema coverage at 0%, the description carries the burden and does add meaning: 'The id is the one the previous call returned.' This clarifies the id's provenance beyond the schema's bare 'as returned by get_radar_matches', though there is only one parameter so the surface for added detail is small.

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?

States a specific verb (undo) and resource (radar match verdict), and spells out exactly what is reversed: a skip, save or defer. This clearly separates it from siblings like skip_radar_match, save_radar_match, archive_radar_match and delete_radar_match without needing to open any schema.

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?

Explains the triggering context (after a skip, save or defer) and explicitly notes that a save-started vacancy analysis is NOT undone, which is a crucial when-to-use boundary. It does not, however, name the alternative tools by name, so it falls just short of explicit routing guidance.

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