continue_last

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

With no annotations, the description carries the full burden, and it delivers meaningful disclosure: the quota note ('🟡 2-3 writes') reveals this is a mutation operation, that it is best-effort, and that it may perform play plus shuffle/repeat. This goes well beyond the generic schema, though it does not cover failure cases like a missing checkpoint.

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 sentences with zero waste: the action is front-loaded, the sibling relation is one clause, and the quota constraint is one compact line. Every sentence carries distinct information an agent needs before invoking.

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 low-complexity tool (3 optional params, no required params, no output schema, no nested objects), the description covers the core behavior, the quota cost, and the sibling relationship. Minor gaps remain — what happens when no checkpoint exists and what the response contains — but the response_format param partially mitigates the latter.

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%, so the baseline is 3 and the schema fully documents dry_run, device_id, and response_format. The description adds only indirect value by explaining why no checkpoint-name parameter exists ('without knowing its name'), which is meta-context rather than parameter-level 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?

States a specific verb (Resume) + resource (most recent checkpoint) and adds the key differentiator 'without knowing its name.' The sidecar lookup mechanism is specified, and naming checkpoint_playback as its pair immediately distinguishes it from that sibling without needing to inspect either schema.

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 phrase 'without knowing its name' clearly frames the selection criterion for this tool versus name-based alternatives like checkpoint_playback, and 'Pairs with checkpoint_playback' gives the collaborator context. However, it stops short of an explicit when-to-use/when-not-to-use statement, leaving the exclusion logic to inference.

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