v2_speedtest

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

Adds real behavior beyond the annotations: it discloses the exact failure mode (-1600) and that the tool reports the unsupported state rather than hanging, plus a READ-ONLY MODE that returns the payload instead of sending it. That is meaningful operational context an agent cannot derive from readOnlyHint/openWorldHint. The mild tension between the annotation readOnlyHint=false and the description's READ-ONLY MODE note is a dry-run/harness distinction rather than a direct contradiction, but it is not fully reconciled.

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 lead sentence is tight and front-loaded, but the definition then carries a long parenthetical caveat and a bracketed mode note that read more like internal maintenance annotations than agent-facing guidance. It is not bloated, but the caveats crowd out the practical details.

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 and no parameter documentation, the description compensates partially by explaining the failure path and read-only behavior, which is the most important thing for this currently-broken tool. It still leaves the agent without any information on inputs or what a successful result looks like.

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 0% and the description never mentions siteId or waitSeconds. The phrase 'poll for the result' faintly implies a timeout/interval parameter, but no units, defaults, or polling semantics are given, so the two parameters remain effectively undocumented.

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 and resource ('Run the controller WAN speed test and poll for the result'), which is concrete enough to distinguish it from generic siblings like v2_wan or v2_diagnostics. It does not explicitly name an alternative tool, but the purpose itself is unambiguous.

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?

Gives unusually strong when-not-to-use guidance: the tool is verified unsupported on this build (-1600) because no Omada gateway is present, and is only retained for future ER-series adoption. It lacks an explicit pointer to what to use instead (e.g., v2_wan or v2_diagnostics), which keeps it from a 5.

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