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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety class is known, yet the description still adds substantive behavior: no vias are added or removed, changes that would split a pour are rolled back, and the board is kept only if the DRC count does not worsen. Those rollback and acceptance criteria are exactly the kind of transactional detail an agent cannot get from annotations.

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 'After routing:' lead front-loads the trigger, and the parenthetical enumerates the widening strategies efficiently. It is a single very dense sentence with heavy semicolons and parentheses, which is a slight readability cost, but virtually no clause is filler.

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 destructive mutation with no output schema, the description covers what changes, what is deliberately left alone (vias), what is reverted (pour splits), and the acceptance condition. Combined with a fully documented schema, an agent has enough to invoke it confidently.

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 100% and both parameters (design_id, wait_s) are documented in-schema, including the job-polling follow-up via get_board_job. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 names the concrete transformations precisely: re-drawing runs as the fewest 0/45/90-degree segments and widening tracks below their netclass width. That is far more specific than the title 'Tidy the copper', but it never distinguishes itself from siblings such as cleanup_board, widen_nets, or polish_vias, which an agent may reasonably consider equivalent.

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?

'After routing:' implies the sequencing context, which is a genuine usage cue. However, there is no explicit statement of when to prefer this over widen_nets or cleanup_board, nor any exclusion such as 'do not run before fill_zones' — the agent must infer placement in the workflow.

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