design_live_snapshot

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

With no annotations, the description carries the full burden and does so well: it discloses that only expect_file calls the bridge, that the read takes a few seconds on a large board, that it refuses if another board is focused, and why it is never invoked standalone (past scripting-engine crashes). It does not say whether published versions can be reverted or what permissions are needed, which is the only remaining gap for a state-mutating tool.

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 with purpose, then behavior, then Args/Returns, with no filler sentences. It is on the long side with some nested parentheticals and indirection around 'the last engine job', but nearly every clause adds decision-relevant information.

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?

Covers all three invocation modes, the causal caveat about the bridge read, failure/refusal behavior, and error shape, so an agent has everything needed to call it correctly. An output schema exists, so the brief return summary is a bonus rather than a requirement.

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 compensate and it does: every parameter gets meaning beyond its name — note is also logged as a decision, board_json_path accepts .json or .json.gz, expect_file must be the full path of the focused board and fails on focus mismatch. The mutually-exclusive default case is also spelled out.

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 specific verb and resource (publish a board to the live view as its next version) and immediately scopes it against the placement/routing jobs and their apply tools that publish on their own. An agent can tell exactly what this tool is for relative to design_live_view and the job apply tools 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?

Explicitly enumerates the three cases this tool is for — the board as it is in the EDA now (expect_file), a saved LayoutBoard JSON, or a re-publish with a note — and states the alternative path (jobs/apply tools publish themselves). The 'Neither: republish the last board' case removes the last ambiguity about default behavior.

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