checkpoint_state

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

No annotations provided, so description carries full burden. It discloses file format (gzipped JSON) and size (~50-200 KB), and mentions what is included. However, it does not explain whether checkpoints overwrite, how many are kept, or any side effects.

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?

The description is structured with a concise one-liner, a bullet list of contents, and an args section. It avoids unnecessary words and is easy to scan. A bit more detail could be added, but it remains effective.

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?

The tool has an output schema (not shown) so return values need not be explained. Parameters are adequately described. However, missing information about whether checkpoints can be resumed multiple times or if calling repeatedly causes conflicts detracts from completeness.

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?

Input schema has no descriptions (0% coverage), but the description clearly explains both parameters: 'task_description: What the agent is working on' and 'current_step: Where in the task it currently is'. This adds significant meaning beyond the empty schema defaults.

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 clearly states the tool's action: 'Save current state to disk for crash recovery and session resume.' It specifies the verb 'save' and the resource 'state', and distinguishes it from sibling tools like 'resume_state' which restores state.

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 description lists what is saved (fragments, dedup index, etc.) but does not explicitly state when to use this tool vs alternatives like 'resume_state' or 'remember_fragment'. Usage context is implied but not guided.

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