show_findings

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

Adds substantial context beyond annotations: it warns that the selection is REPLACED, discloses the KiCad 10 limitation where highlight and zoom return unsupported_on_this_kicad while selection still happens, explains that stale findings (pcb_sha256 mismatch) are still resolved and flagged possibly_stale, and describes the per-finding result shape. This is consistent with readOnlyHint=false (it mutates the editor selection) and destructiveHint=false, with no contradiction.

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?

Purpose and the selection-replacement warning are front-loaded, and nearly every sentence carries distinct operational information. It is dense with multi-clause sentences and could be broken into shorter units for scanability, but there is little pure 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?

There is no output schema, so the description covers return values itself (resolved items, unresolved locators with reasons, action taken, totals). Combined with the mode/focus/zoom semantics, the KiCad-version fallback, the stale-finding behavior, and the optional-location case, an agent has everything needed to call this 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 0% and the schema has no descriptions or enums, so the description must carry the load — and it does: it enumerates mode values (select | highlight | both), focus values ('all', a finding index, 'next', 'previous'), zoom as true/false, and the three accepted forms of findings. It also clarifies that a finding's location is optional and what a null location means.

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?

Opens with a specific verb and resource: 'Point the user at kicad-tools findings in KiCad's PCB editor', then states the mechanism (resolve locators against the live board, select affected items). No sibling (session_status, board_summary, get_selection, etc.) does anything comparable, so the tool is unambiguously distinguishable.

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?

Gives concrete input provenance — findings must be the JSON printed by 'kct check / drc / detect-mistakes / net-status --format json', or a list of its findings — which effectively tells the agent when this tool applies. It does not explicitly state when to prefer a sibling (e.g. get_selection) or when not to use it, so it stops short of a 5.

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