Checkpoints

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

Annotations only declare destructiveHint=true and openWorldHint=false; the description adds substantive behavior on top: restore first snapshots current state (making it recoverable), restore refuses when the file is open in KiCad (a precondition the agent must satisfy), and writes are auto-checkpointed. Not covered: retention/cleanup of snapshots or what happens on id collisions.

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 one-line purpose, then per-action grammar separated by ·, then a single worked example. Dense and almost waste-free; the multi-line action block is slightly harder to scan than a bulleted list would be, but nothing is redundant.

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, yet the description implies list/diff return something without saying in what form (file names? unified diff? ids?), which is the main gap. Everything needed to invoke the tool correctly — action semantics, required id for restore, precondition on open files, auto-snapshot behavior — is present.

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 only 25% (just 'project'), so the description must compensate, and it largely does — every action enum value is explained, plus id optionality/defaults per action and label optionality. 'project' is left to the schema and the purpose of 'label' (how it is surfaced in list) is unstated, so not a full 5.

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 concrete verbs (snapshot/list/diff/restore) against a named resource (the project's design files, enumerated as .kicad_sch, .kicad_pcb, .kicad_pro, rules, lib tables) and names the storage location (.copper/snapshots). An agent can immediately tell this is the versioning tool and not any of the pcb_*/sch_* editing siblings.

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?

Each action is scoped: 'create' with optional label, 'diff' with optional id defaulting to newest, 'restore' requiring id. It also gives a key routing hint — mutating tools snapshot automatically before they write — telling the agent it need not call checkpoint before every edit. It lacks an explicit statement of when NOT to use it (e.g. use project_summary to inspect state instead), so it falls short of 5.

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