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

The description discloses important behavioral traits beyond annotations: re-wiring an existing edge updates its kind/guard in place, `remove: true` drops the edge, and the tool returns a fresh summary with full edge topology while the Builder canvas updates live. This goes beyond the plain readOnly/destructive hints and does not contradict them, though it could add more about error cases or reversibility.

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 description is dense but every sentence earns its place: core operation, endpoint identifiers, guard semantics, removal mode, update behavior, return value, live canvas update, and sibling differentiation. There is no filler or unnecessary repetition.

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?

Despite having no output schema, the description explains what is returned (fresh block-by-block summary including full edge topology) and what happens live in the Builder. It covers preconditions, parameter semantics, and the key behavioral nuance of updating existing edges, making it sufficient for correct invocation.

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 100%, so the baseline is 3. The description adds useful semantic framing around `guard` as a conditional loop exit condition and explains how to identify endpoints by node id, label, skill name, or position. Some details repeat the schema, but the extra context helps an agent select parameter values correctly.

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 opens with a specific verb and resource: 'wire or unwire ONE edge between two EXISTING blocks of a canvas rig.' It also explicitly differentiates this tool from rig_node_add by stating that rig_node_add's `after` only wires at creation, so an agent can immediately identify which tool handles rewiring.

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 description gives clear usage context: it applies to existing blocks, supports both wiring and unwiring, and names the alternative tool with the exact reason to prefer this one for rewiring. Examples like 'connect the fetch step to the judge' and 'disconnect A from B' make the intended invocation scenarios concrete.

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