export_positions

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

Annotations already declare destructiveHint=false, idempotentHint=true, openWorldHint=false, so the safety profile is covered; the description adds real value by documenting coordinate units, the negated Y axis and per-column semantics. The notable gap is file behavior: it never says what filename is produced, whether an existing file in output_dir is overwritten, or what happens if the directory doesn't exist — significant for a tool with readOnlyHint=false.

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 purpose, then format details, then args — a sensible order with no filler. The per-column gloss (PosX/PosY/Rot/Side) is slightly repetitive after the column list but earns its place by defining the negated-Y convention.

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?

An output schema exists, so return values needn't be described, and both parameters plus the CSV semantics are covered. What remains missing for a file-writing export is the destination filename and overwrite/error behavior, which an agent would need to call 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 0% — the schema only has titles and empty-string defaults — so the description must compensate, and it does: it identifies pcb_path as a path to a .kicad_pcb file and output_dir as an output directory, and marks both optional with 'omit to use the configured default'. It stops short of explaining what the configured default actually resolves to or how the output filename is derived from output_dir.

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 and artifact ('Export component position file (pick and place) as CSV, in millimetres'), and the column list makes the output format unambiguous. This is clearly distinguishable from siblings like export_bom, export_netlist, export_ipc2581 and export_gerbers without opening any schema.

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?

Usage is implied by the artifact produced: an agent knows to call it when it wants a pick-and-place file. However, it never states when to prefer this over export_ipc2581 or export_pcb, and offers no exclusions or preconditions (e.g. board must be loaded/validated). The only guidance is the 'omit to use the configured default' note on both params.

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