agent_checkpoint

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

With no annotations, the description carries the full behavioral burden. It usefully discloses what gets stored (arbitrary JSON: cursor, partial results, plan, open files) and the return value (checkpoint plus monotonic seq), but says nothing about whether it overwrites prior checkpoints, lifecycle/consumption by resume, or permission needs.

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 tight sentences, front-loaded with the purpose, then payload semantics, then return value, then cadence. No filler and every sentence carries a distinct fact.

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?

Given no annotations and no output schema, the description supplies the essential missing context: payload shape, return value, and call cadence. It is largely sufficient for correct invocation, with the only gaps being overwrite/lifecycle behavior.

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 earns extra by expanding `state` into concrete examples (cursor, partial results, plan, open files) and clarifying `summary` as a one-line 'where I am', adding meaning beyond the terse schema strings. It does not address `token_estimate` or `session_id` semantics.

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?

Specific verb ('Snapshot') plus resource ('the agent's working state') with an explicit goal ('so a restart/crash can resume from exactly here'). It distinguishes itself from the surrounding ctx_* and agent_* siblings functionally via the resume framing, though it never names an alternative tool directly.

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?

'Call periodically after each chunk of progress' gives a clear triggering condition for use. There is no when-not guidance and no explicit routing to siblings like agent_handoff or ctx_save, so it stops short of a 5.

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