v2_radar_audit

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

Annotations already declare the safe read-only, idempotent, non-destructive profile. The description adds real behavioral context beyond that: it performs a live watch, correlates uptime with radar hits, reads the v1 event log, and explicitly claims to state its own limits. It still does not describe the returned evidence shape or runtime cost of the live watch.

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?

Four sentences, front-loaded with the value proposition and then the mechanics; it is well-sized and every sentence describes a real action. The opening 'settle a DFS argument with evidence rather than opinion' is slightly rhetorical but still functional framing.

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 read-only audit tool with three parameters and no output schema, the description covers the major behaviors and even flags its own provability limits. It is close to complete, with the remaining gap being the format of the evidence it returns and the undocumented siteId.

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 67%, and the description itself names no parameters. The schema already explains days (default 7) and watchMinutes (default 5, 0 to skip), so the description adds nothing about parameter behavior, and siteId is 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?

The description gives a specific resource (DFS radar/radio audit) and enumerates the concrete actions: reports DFS-channel radios, live-watches for channel changes, checks AP uptime, sweeps the event log. The purpose is clear, but it never distinguishes itself from the sibling v2_dfs_check, leaving an agent to infer the split.

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?

Usage is only implied through the narrative framing ('settle a DFS argument') and the schema note that watchMinutes=0 skips the live watch. There is no explicit when-to-use/when-not guidance and no reference to the obvious alternative, v2_dfs_check.

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