session.checkpoint

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

No annotations, so the description carries the burden and does well: it discloses the mutation side effect (new checkpoint with new ID, refresh of .agent/context/current.md) and the idempotency hazard of duplicate calls. It omits auth/permission expectations and any failure modes, keeping it short of a 5.

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-loads the action and payload before the constraint and the sibling routing; every sentence earns its place. Slightly dense with parenthetical enumerations but no waste.

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, and the description does say it returns the checkpoint JSON, so return expectations are covered. For a no-required-param mutation with zero annotations, it gives sufficient guidance, though permission/auth context and the shape of the refreshed file are unstated.

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 baseline 3 applies, and the description adds real value by naming the captured payload (progress, decisions, blockers, changed files) that flows into next_action's downstream visibility. It doesn't clarify how label is surfaced in later context.

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 a specific verb+resource with full scope: "Snapshot the current work" enumerated as task, progress, decisions, blockers, changed files, next_action, plus the .agent/context/current.md side effect. Clearly distinguishable from session.get, session.record, and context.update 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?

Explicitly says when to call (once at a stopping point, before ending or handing off) and when not to (not as a retry, since every call writes a new checkpoint with a new ID). Also routes to session.record with checkpoint=true when logging event/decision in the same step.

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