v2_diagnostics

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: it is a composite aggregation ('in one call') covering eleven distinct diagnostic areas, which tells the agent this is a heavy, wide-scope read rather than a narrow query. It does not mention latency cost, auth scope, or result size.

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 content is dense but front-loaded with the headline claim ('The 6.2 diagnostic surface in one call') before the metric inventory, and the routing sentence is placed last where it belongs. The long comma-separated metric list is necessary given there is no output schema, but it is verbose and could be grouped.

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's enumeration of returned diagnostics is exactly what the agent needs and it is thorough. Annotations cover the safety profile. The remaining gap is the unexplained siteId parameter and the absence of any note about call cost or result volume for such a broad aggregation.

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?

There is one parameter, siteId, with 0% schema description coverage, so the description carries the full burden of explaining it. The description never mentions siteId, its format, or whether omitting it (0 required parameters) scopes to a default site or returns everything. With low coverage and no compensating text, this is a real gap.

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 resource (the diagnostics surface) and enumerates exactly which metrics it returns, so an agent knows precisely what comes back. It also positions itself against configuration tools with the 'healthy vs configured' framing. It stops short of naming the overlapping siblings it must be distinguished from (v2_rf_health, v2_health_audit, v2_channel_util), so it is clear but not fully differentiated.

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 closing sentence gives an explicit selection heuristic: use this to answer 'is the wireless actually healthy' rather than 'is it configured correctly'. That is a real when-to-use signal tied to the sibling landscape. It does not name a specific alternative tool or state exclusions within the diagnostic space, so it falls short of a 5.

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