design_validate

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

With no annotations, the description carries the full burden and does disclose the composite execution (three underlying operations), the structured ValidationReport shape, and the schematic-only limitation. It does not state whether running ERC has side effects such as forcing a recompile or how expensive the call is, which is the main remaining behavioral unknown for a tool that shells out to three operations.

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 the one-line purpose, then composition, scope caveat, and Args/Returns sections. The Returns block restates a ValidationReport shape that an output schema already defines, so it is slightly redundant, but the description remains tight and scannable.

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 single optional parameter with an output schema present, the description covers what an agent needs: what is run, what is returned conceptually, and the schematic-only scope. Only the side-effect/cost profile of invoking the underlying checks is unaddressed.

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 fully: project_path is documented as an optional absolute path to a .PrjPcb with explicit fallback behavior ('if omitted, uses the focused project'). Format and default semantics are covered beyond the bare string type in the schema.

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+resource ('ERC + connectivity sanity report') and clarifies it is an aggregation of run_erc, proj_get_messages, and get_unconnected_pins into one ValidationReport, which separates it from calling those siblings individually. It also scopes itself to schematic-only work. It does not, however, differentiate itself from other high-level review siblings such as design_audit_schematic, design_lint_report, or review_design.

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?

'Schematic-only in this slice, PCB validation is a separate later slice' gives a clear when-not boundary, and the framing that the planner reads the report implies a planning/review workflow. But it never says when to prefer this over run_erc, proj_get_erc_violations, or the audit/review siblings, leaving the selection decision to inference.

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