Project checkpoints

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

Goes well beyond the annotations: restore never overwrites the original or an earlier restore, retention is capped at the 50 latest, restore-without-id defaults to the latest, and the unsaved-changes guard is disclosed. The destructiveHint=true annotation is consistent with discardChanges discarding unsaved edits rather than with overwriting files.

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 action enumeration and the safety rule before the operational details. It is dense with nested parentheticals, which costs a little readability, but essentially every clause carries operational information.

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?

No output schema exists, and the description compensates by stating what save returns (id and file) and what list returns (ids, times, labels). Preconditions, defaults, retention and side effects are all covered for a 4-parameter, three-mode tool.

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 100%, so the baseline is 3, but the description adds real semantics: omitting `id` on restore selects the latest, `discardChanges` overrides the unsaved-changes refusal, and `label` is only meaningful for save. Only the exact id format is left to 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?

Names the resource (project checkpoints) and enumerates the three concrete operations with verbs: save, list, restore. The parentheticals define what each verb actually does (save = save project then snapshot; restore = opens a NEW file), so it is clearly distinguishable from siblings like ae_undo.

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 an explicit when-to-use rule ('Use before large or risky changes'), a prerequisite ('The project must have been saved once'), and routes the agent elsewhere for the adjacent case ('To revert just the last edits use ae_undo'). It also states the restore precondition (refuses with unsaved changes unless discardChanges).

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