Write a PcbLib

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

Annotations only signal destructiveHint=true and readOnlyHint=false, but the description discloses far more: append semantics, automatic designator insertion on Top Overlay, auto_3d_body placeholder behavior (1.0 mm, assumed_height flag), the response 'bodies' source reporting ('none' when no STEP/body), the silk-on-pad warnings array, and the '|' separator restriction. This is rich behavioral context that materially affects how the agent uses the tool and interprets results.

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 long but every sentence carries actionable information, from append mode to units to the '|' separator constraint. The primary verb and resource are front-loaded in the first sentence. It loses a point for being a single dense paragraph — the auto-designator, auto-3D-body, and response behavior could be separated for easier scanning — but no sentence 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?

Despite having no output schema, the description covers the response contract ('bodies' array, 'warnings' array) and all critical behavioral edge cases: library replacement vs append, designator auto-placement, read-echo preservation, 3D body fallbacks, units, and the separator restriction. For a write tool of this complexity, nothing essential is missing for an agent to invoke it 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 description coverage is 100%, so the baseline is 3, and the description adds meaningful value beyond it: it specifies that all coordinates/dimensions must be in mm, that the AI must calculate positions per IPC-7351B, and it explains the practical intent of auto_designator, auto_3d_body, and append. These details are not fully captured in the schema property descriptions, so the description genuinely supplements 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?

The opening sentence states a specific verb and resource: 'Write footprints to an Altium .PcbLib file.' It clearly distinguishes this from the read/schlib siblings by naming the exact file type and the append-vs-replace behavior. The scope (pads, tracks, vias, fills, arcs, regions, text, component_bodies) is enumerated, leaving no ambiguity about what the tool operates on.

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?

The description gives clear guidance on the key usage decision ('set append: true to add to an existing library instead of replacing it') and explains when auto_designator and auto_3d_body should be toggled, including the important read-echo exclusion (a footprint carrying primitive_order is never touched). It doesn't explicitly name sibling alternatives like write_schlib, but the context is clear enough that an agent can select this tool for PcbLib authoring without inference.

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