checkpoint_work

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

With no annotations, the description carries the full behavioral burden, yet it only establishes that this is a write ("Persist"). It says nothing about idempotency, whether a new checkpoint supersedes prior ones, retention or overwrite behavior, required permissions, or any rate/ordering constraints — all material for a crash-recovery write.

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, and the primary purpose statement is front-loaded ahead of the constraint. It is efficient, though the brevity shades into under-specification rather than disciplined editing.

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?

For a six-parameter, nested-object mutation with zero annotation coverage and zero schema descriptions, the description is far too thin. It covers the work_ref prerequisite but leaves the agent without enough context to construct payload, kind, or the plan/turn linkage 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% across six parameters, so the description must compensate and largely does not. The single constraint it adds (the reference must map to an existing canonical WorkIdentity) clarifies work_ref, but kind, payload, plan_id, turn_id, and actor_id remain entirely unexplained.

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 gives a verb ("Persist") and a resource ("crash-recovery state"), so the general intent is inferable, but "PROGRESSIVE crash-recovery state" is jargon that never says concretely what is being written (a snapshot? a delta? a pointer?). It also does nothing to separate this from siblings such as begin_work, bind_work_turn, or backfill_work_identity.

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 second sentence supplies a real precondition — the work reference must already exist as a canonical WorkIdentity — which implies when this tool is valid versus when it is not. However, no alternative tool is named for the otherwise-implied case, and there is no guidance on when a checkpoint should be taken relative to begin_work or bind_work_turn.

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