Commit session

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

Beyond the annotations, the description discloses that every call adds a new checkpoint (reinforcing and explaining the non-idempotent hint), that checkpoints are ephemeral and vanish when the session closes or expires, and what the response contains. This is exactly the kind of consequence-level context annotations cannot convey.

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?

Four sentences, each carrying distinct information: what it does, the return shape and rollback path, the append-only nature, and the persistence caveat with the save_to_library follow-up. The most decision-relevant facts are front-loaded and nothing is padding.

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?

With no output schema, the description compensates by naming the returned fields, and it covers the lifecycle risk (checkpoints lost on close/expire) plus the follow-up call needed for durable versions. Nothing an agent needs in order to use this correctly is missing.

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 100% and both parameters are documented there, including the dual role of message as the next Library version's name. The description restates that role rather than extending it, so the schema is doing the heavy lifting and the baseline of 3 applies.

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 opens with a specific verb and resource: 'Create a named checkpoint of the session's current state.' An agent immediately knows the operation. It does not, however, distinguish this from the sibling tool snapshot_session, which sounds like it does something closely related — that ambiguity keeps it from a 5.

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?

It gives a concrete usage moment ('e.g. before a risky edit') and explicitly routes the agent elsewhere for two adjacent needs: restore_session for rollback and save_to_library for persistence. What's missing is any guidance on when to choose commit_session over the sibling snapshot_session, which is the most likely point of confusion.

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