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

With no annotations, the description carries the full burden and does well: it discloses the returned fields, the conditional read-vs-fresh-start behavior, and a plan gate (Pro). It does not state that the call is side-effect free or what happens on an invalid/failed lookup, which are the remaining 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?

Three short sentences with the critical directive front-loaded first, followed by the two outcome branches. No filler, though the phrasing is slightly dense in the middle clause.

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 single-parameter tool with no output schema and no annotations, the description covers purpose, ordering, branching behavior, returned fields and the Pro requirement. Only error/failure behavior and the read-only nature are left implicit.

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 run_id already documents stability across restarts with an example. The description reinforces run_id's role as the lookup key but adds no new syntax or format detail, so the baseline 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?

States a specific verb-and-resource behavior: it reads a checkpoint for run_id and returns the last step, state and done list, otherwise starts fresh. This distinguishes it cleanly from list_checkpoints and save_checkpoint, which are the adjacent checkpoint tools.

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 FIRST when a run starts" gives explicit ordering guidance, and the checkpoint-exists/does-not-exist branches tell the agent how to proceed in each case. It stops short of naming siblings as alternatives, but the when-to-use condition is unambiguous.

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