v2_set_site_feature

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

Annotations already declare idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing the dry-run behavior (payload returned rather than sent), but it omits partial-update semantics – i.e. whether omitted boolean flags are left untouched or reset – which matters for a 15-param toggle tool.

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 compact sentences, feature list front-loaded, dry-run caveat placed last where it reads as a mode modifier. Minimal waste, though the feature enumeration is long and slightly dense.

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 15-parameter, zero-required mutation tool with no output schema and 13% schema coverage, the description covers the feature surface but not the update contract (partial vs full replacement), the meaning of the threshold parameters, or whether siteId is required. Adequate but with clear gaps.

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 only 13%, so the description must compensate. It does map feature names to several parameters (airtime fairness per band, alert logging, remote syslog target, LED, LLDP, auto-upgrade, band steering), which helps, but the threshold, port, and server parameters remain undocumented in both schema and description.

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 clear verb (toggle) and resource (site-wide features) and enumerates the specific feature set – airtime fairness, alert logging, remote syslog, LED, LLDP, auto-upgrade, band steering. It does not, however, differentiate itself from siblings such as v2_site_settings or v2_set_service, which could plausibly overlap on site-level toggles.

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 '[READ-ONLY MODE: returns the exact payload instead of sending it]' note implies the dry-run path, and the feature list implies when to reach for this tool, but there is no explicit when-to-use vs when-not, no mention of v2_site_settings or other setters as alternatives, and no statement about which parameters must be supplied.

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