Lint Offgrid

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

Despite destructiveHint being true in annotations, the description adds significant behavioral context: it clarifies that fixes are 'byte-exact text splices' that preserve formatting, that '(lib_symbols) content and property field positions are never touched', and that there's a 0.5 mm safety threshold for auto-snapping. This goes well beyond the annotation and informs the agent exactly what side effects to expect.

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 description is structured as three dense but well-organized sentences. It front-loads the core function, then explains the rationale and limitations. There is no wasted text; every sentence contributes essential information about purpose, safety, or differentiation.

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?

The description covers the tool's main function, optional fix behavior, why it matters (junction placement poisoning), what it does not modify, when it refuses to auto-snap, and how it relates to snap_to_grid. With an output schema present to describe return values, this is a complete and self-contained description for an agent to select and invoke the tool correctly.

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 100% (each parameter has a description), which gives a baseline of 3. The description adds valuable context: it explains why gridSize defaults to 1.27 mm ('KiCad's connection grid is fixed at 50 mil') and what fix:true does ('snap them to the nearest grid point'). This enhances the meaning of the parameters beyond the schema, though not exhaustively.

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 clearly states the tool's purpose: 'Report every off-grid connection-relevant coordinate in a schematic' and lists specific element types (wire/bus endpoints, symbol origins, label/junction/no_connect anchors). It also distinguishes itself from sibling snap_to_grid by contrasting its byte-exact fix behavior, eliminating ambiguity about what the tool does and how it differs.

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?

Provides explicit alternative guidance: 'Unlike snap_to_grid (whole-file rewrite), fixes here are byte-exact text splices that preserve file formatting.' It also explains when auto-snapping is unsafe ('Offenders more than 0.5 mm off-grid are reported as NEEDS HUMAN and never auto-snapped'). However, it doesn't fully enumerate when not to use this tool versus other linting/reporting tools beyond snap_to_grid, so it's not a 5.

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