Save Checkpoint

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

No annotations, so the description carries the burden. It does disclose a real behavioral trait — the checkpoint survives a restart and is meant for a fresh session — which is genuinely useful context. It omits whether saves overwrite a prior checkpoint, whether 'verified' gates anything, and what the call returns, which are material for a persistence tool.

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, each earning its place: the purpose first, then content requirements, then a single prohibition. Nothing redundant.

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 4-parameter write with no output schema, the description covers intent, content shape, and a key content exclusion, which is enough to call it correctly. The missing piece is how checkpoints relate to existing ones and to the progress-reporting siblings.

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 75%, so the schema already documents summary, details, and verified. The description adds the useful negative constraint ('do not paste raw last output') and enumerates the content expected inside details, but says nothing about taskId or the semantics of the verified flag beyond what the schema states.

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 (persist verified progress) plus the reason it exists: letting a new session continue after a restart. It does not explicitly distinguish itself from the sibling report_progress, which is the nearest confusable tool, so it stops short of a 5.

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 purpose sentence implies the trigger (end of a work segment, before a restart) but never states when to use this versus report_progress or report_interruption. The remaining sentences are content guidance ('include concrete details', 'do not paste raw last output') rather than usage routing.

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