pt_build

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

With only openWorldHint=false in annotations, the description carries most of the burden and does add real behavior: ports auto-picked when omitted, configs applied and saved, `auto` invoking pt_auto_address after cabling, and checks executed only when verify=true. It never says whether an existing topology is cleared or appended to (pt_clear_canvas is a sibling, making this ambiguity material), nor what happens on partial failure — the main remaining gap.

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 purpose sentence is front-loaded and the dense spec block earns its space by encoding structure that the free-form schema cannot. Inline comments are terse and functional, though the block is heavy enough that the key behavioral note about pt_auto_address trails at the end rather than appearing where the `auto` key is defined.

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 high-complexity, nested-object tool with no output schema and near-zero annotation coverage, the spec shape is well conveyed but critical operating facts are absent: return value, whether the canvas is reset first, minimum viable spec (are devices/links required?), and failure/rollback semantics. An agent can construct a spec but cannot predict the side effects with confidence.

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 0% and spec is a free-form object with additionalProperties, so the description must do all the work — and it does, documenting six top-level spec keys with sub-field hints and `?` marking optional members (x?, y?, a_port?, b_port?). The only weak spots are that the verify parameter is only indirectly implied via 'run when verify=true' and no key is marked required.

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 opening sentence is a specific verb plus resource with explicit scope — 'Build a whole network in one call' — which separates it from the incremental siblings pt_add_devices, pt_connect and pt_add_module. The spec block then enumerates exactly which artifacts it creates (devices, links, configs, hosts, addressing, checks), so an agent knows the full surface without opening the 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?

Usage is implied rather than stated: 'in one call' plus the presence of pt_add_devices/pt_connect as siblings suggests this is the batch alternative, but the description never says so explicitly or names a when-not condition. It does clarify the internal sequencing with pt_auto_address and the verify=true trigger for checks, which is useful, but the build-vs-incremental decision 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.