get_selection

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

Beyond the readOnlyHint annotation, the description discloses substantive behavior: non-file items get session-scoped ids with no_file_reference: true, undescribed items are counted and never silently dropped, bbox is reported in mm in the file frame with a board-frame offset, and an empty selection is not an error. These are exactly the traits an agent cannot infer from the structured fields.

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 core action, then a dense enumeration of return categories, then the filter notes. It is a single long paragraph, but nearly every clause carries distinct information; only the kind enumeration is heavier than strictly necessary.

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 describe the return shape, and it does: reference designators, 'REF.PAD' strings, net sets, session ids, and mm bbox with frame offset. Combined with the empty-result and undocumented-item notes, an agent has enough to call and interpret results 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 0%, so the description carries the burden and largely does: it gives an example kinds value ('footprint', 'pad') and explains that include_geometry adds per-item positions and boxes. Minor gap in not enumerating the full set of valid kinds strings or clarifying filter behavior for unknown kinds.

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 resource ('Read what is selected in KiCad's PCB editor') and enumerates the exact categories returned (footprints, pads, nets, nets_of_footprints, other, undescribed, bbox). No sibling tool (session_status, board_summary) could be confused with this targeted selection read.

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 rather than stated: 'live' reads plus 'references that kct commands accept' hint at when it is appropriate, and 'An empty selection is an ordinary empty result' pre-empts a common misread. However, it never names an alternative or an explicit when-not condition relative to siblings like board_summary or show_findings.

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