app_checkpoint

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

With no annotations, the description carries the full burden and does: it discloses content-addressed dedup and cheap repeat checkpoints, notes that a checkpoint is taken even if the flush fails, and warns that a post-failure checkpoint holds only on-disk state — precisely the failure mode that matters. That is behavior an agent could not infer from name or schema.

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 key guidance is front-loaded in the first paragraph, and the Args/Returns blocks are dense rather than padded. Slight over-explanation in the save_error/note walkthrough keeps it from a 5, but nothing is wasted for a mutating tool with no annotations.

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?

Covers what is snapshotted, the storage model, the risk-mitigation use case, both parameters, and the failure return shape. An output schema exists, yet the extra note about the `saved`/`save_error` fields adds decision-relevant nuance rather than merely restating it.

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 must compensate and does: it explains `label` with an example, and explains `save_first` including its default True and the reason for it (flush dirty Altium docs so in-editor changes are captured). Meaning is added well beyond the bare type/default in 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?

Opens with a specific verb and resource ('Snapshot the focused project') plus the purpose (session revertibility), and names the counterpart tool app_restore_checkpoint. A reader can immediately tell this apart from save tools like app_save_all or proj_save.

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?

Explicitly states when to take one ('before any risky autonomous edit') and how it relates to the alternative ('restore with `app_restore_checkpoint`'). It also frames it as the undo the live bridge lacks, which disambiguates it from the design/review snapshot tools.

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