pcb_set_mech_layers

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

No annotations exist, so the description carries the full burden and does: it discloses per-layer read-back verification with per-layer failure reporting rather than an aggregate pass, the paired-kind storage model (side dropped, pair held jointly), the requirement to supply both sides in one call, and the orphaning hazard when a kind moves off a layer carrying geometry. This is precisely the context an agent cannot get from the schema.

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?

Front-loaded verb statement followed by labeled sections (PAIRED KINDS, READ THE BOARD FIRST, Args, Returns) make it scannable despite its length. Minor deduction: the sentence contrasting what a board 'could only have' without this tool is rationale the caller does not need, and the Returns block partly duplicates the output schema.

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 mutation tool with no annotations and a 0%-documented schema, the description covers preconditions, per-parameter semantics, failure semantics, destructive-option warning, and the domain trap (paired kinds / orphaned geometry). An output schema exists, so describing return keys is a convenience rather than a gap-filler.

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 layers is an untyped object array, so the description must compensate entirely — and it does: it enumerates the allowed keys (layer required, e.g. 'Mechanical13'; name; enabled bool; kind e.g. 'Courtyard Top'), defines the empty-dict case ('reported as nothing asked for'), and explains tidy_pairs' destructive default and units for timeout.

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?

Opens with a specific verb triple plus resource and scope: 'Name, enable and kind the mechanical layers of the open BOARD.' It immediately names the two siblings it must be distinguished from (lib_set_mech_layers, pcb_set_mech_layer_kind) and states exactly what those cannot do, so the agent can route without opening a schema.

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?

Explicit when-to-use versus named alternatives, plus a stated prerequisite workflow ('READ THE BOARD FIRST' with pcb_get_mech_layer_names) and a clear when-not/why-not for tidy_pairs ('Off by default, because it REMOVES pairs'). Nothing about selection is left to inference.

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