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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, and the description still adds real behavior: results are truncated to 'the first violations' with a default cap of 40, and a second mount_fit check is disclosed with its concrete tolerance (0.2 mm milling). It does not disclose that this is a long-running job whose result may come back as 'running' — that lives only in the wait_s schema text.

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 core purpose and output shape are front-loaded in the first clause, with the mount_fit addendum after. It is dense and long-ish, but nearly every clause carries information; the only soft spot is the mount_fit tangent competing with the primary DRC purpose.

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?

There is no output schema, so the description must explain the return value — and it does, enumerating counts by type, shorts, unconnected items, parity items, and truncated violation records with items and positions. The one gap, job follow-up via get_board_job, is covered by the wait_s schema text rather than the description.

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 50%: design_id and wait_s are documented, but types and max_violations are not. The description compensates by explaining that types is a filter over violation kinds and max_violations caps how many violations are returned, with a default of 40 — adding meaning beyond the bare integer bounds.

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 opens with a specific verb and resource — 'KiCad's DRC on the board as it is now' — plus the schematic-parity caveat, and it names the concrete outputs (counts by type, shorts, unconnected items, parity items, violations with positions). It never names the adjacent siblings (check_net_rules, check_physics, diagnose_open_nets), so the agent must infer the DRC-vs-rule-check distinction itself.

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?

'On the board as it is now' implies a post-edit / pre-signoff check, and the parity clause hints when the schematic is needed, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many check_* siblings. Usage is implied rather than stated.

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