confirm_pour_step

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

Goes well past the annotations: it discloses the scratch-copy semantics (source untouched), the single-use token, the cost profile (~12 gate runs, capped at 40, minutes not seconds), and precisely what `poured` does and does not prove (no pad proven isolated, but connectivity may still be `unproven`). It also warns that both gates are stale until verify_board runs — behavior an agent could not infer from destructiveHint alone.

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-loads the action and scratch-copy semantics, then layers preconditions separately from the meaning of `poured`. Dense but almost every clause is load-bearing; it runs slightly long, though the detail is justified for a destructive, minutes-long operation.

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?

With no output schema, the description compensates by explaining pcb_path vs source_pcb and the pads connectivity field, plus the stale-gate caveat — all things an agent needs to act on the result. The one real hole is the unexplained `parity`/`parity_reason` parameters, which the description never addresses.

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%, so the description must carry all parameter meaning. It explains baseline (dict from pin_rule_baseline, required), revision_token (single use), and pcb_path (the board passed in), but `parity` (enum required/not_applicable) and `parity_reason` are never mentioned, leaving two of five parameters undefined anywhere.

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 concrete verb chain (run router on a scratch copy, grade candidate, conditionally write a NEW revision) and the resource (board revision with the poured zone). It also explicitly bounds the scope against siblings by noting the source is untouched and that only verify_board certifies a board, so an agent can distinguish it from propose_pour_step and verify_board.

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 explicit preconditions (baseline from pin_rule_baseline is required, propose_input_preparation must have run, copper-layer text is refused) and when-not conditions (empty baseline refused, single-use token, over the run cap a pad is never accepted unproven). It also names the alternative that actually certifies a board: verify_board.

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