Commit Document

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

With no annotations provided, the description carries the behavioral burden. It discloses that the tool creates a timestamped snapshot and stores it in CAS, and it explains supported input types. It does not mention side effects on the draft/source, immutability, idempotency, or permission requirements, so there are clear gaps.

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?

Two sentences, no filler, with the core action front-loaded and the supported input modes stated explicitly. Every sentence adds meaningful 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?

The tool has six parameters, zero schema descriptions, and no annotations, yet the description leaves most parameter semantics unexplained. Output schema existence reduces the need to describe return values, but an agent still lacks essential guidance on how to fill parameters 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%, and the description does not explain the roles of target, message, mode, author, content, or is_pinned. The mention of disk files and virtual memories hints at how target/content might be used, but it is not enough to compensate for the complete lack of parameter documentation.

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?

The description states a specific action: 'Crée un instantané horodaté d'un document dans le CAS', identifying both the resource (document) and storage context (Content-Addressable Storage). It also distinguishes this tool from sibling tools like list_commits, restore_commit, and prune_commits by emphasizing creation of a snapshot.

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?

The description gives useful context about when to use the tool: it supports disk files and virtual memories/drafts without a file. However, it does not explicitly state when not to use it or point to an alternative among the sibling tools, leaving selection guidance only implied.

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