v2_set_switch_stp

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

Annotations only cover idempotency/safety flags; the description adds substantive behavior the annotations cannot convey: the ~30 s convergence window, the concrete blast radius (AP/camera ports drop), the root-bridge rule (lower priority wins, 4096 forces root), and a dry-run/read-only mode that returns the payload instead of sending it. That is exactly the extra context an agent needs for a disruptive network mutation.

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?

Highly dense: action first, then the disruptive-behavior warning, then the mode note. Almost every clause carries information. The bracketed '[READ-ONLY MODE: ...]' is slightly cryptic and left unexplained relative to the dryRun parameter.

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 6-parameter state-changing tool with no output schema and sparse annotations, the description covers the headline semantics well but leaves half the parameters undocumented (mode enum values, dryRun vs. READ-ONLY MODE, siteId). 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 description coverage is only 17%, so the description must compensate but only partially does. It adds real meaning for priority (lower wins; 4096 forces root) and implies the on/off semantics of the operation, but says nothing about the mode enum (off/stp/rstp/mstp), dryRun, siteId, or switchMac.

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 specific verbs and resource: enable/disable STP, set bridge priority and timers on a switch. An agent immediately knows the domain of change. It does not contrast itself with any sibling tool, but the sibling list contains no other STP-specific writer, so the lack of differentiation is a minor gap.

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 clear situational guidance: enabling STP causes ~30 s of listening/learning and will drop ports carrying APs/cameras, so it should be run 'when the network is quiet.' This is actionable when-to-use context. It stops short of naming an alternative tool or stating an explicit when-not-to-use rule.

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