task_save

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

No annotations are present, so the description must carry the full burden. It does disclose important behaviors: expected_revision rejects stale saves, progress is appended, messages append to conversation.jsonl, and artifacts are snapshotted. However, it doesn't clarify overwrite vs. merge semantics for the entire task state or behavior when the task doesn't exist, leaving some behavioral ambiguity.

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 well-structured: an action line, a trigger sentence, guidance on the context parameter, and a detailed Args list. Each section adds value, though the initial context guidance slightly overlaps with the context parameter description, preventing a perfect score.

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 tool with 9 parameters and no annotations, the description covers purpose, triggers, and all parameter semantics, and even adds a concurrency note. The output schema exists, so return values need not be explained. However, it omits the relationship to task_init/task_load and failure behavior, leaving some context gaps.

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 0%, but the Args section provides meaningful descriptions for all 9 parameters, including formats (e.g., '/abs/path', list of strings) and semantic guidance (e.g., 'distilled, not raw conversation'). This fully compensates for the schema's lack of descriptions.

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 states 'Save the current state of a task' with a specific verb and resource, clearly identifying the action. The trigger phrasing ('when the user says "save"') also differentiates it from sibling tools like task_load and task_init.

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?

It provides explicit trigger conditions: 'Call this when the user says "save", "保存", or wants to checkpoint progress.' This is clear usage guidance, though it does not explicitly mention alternatives or when not to use it. The context is sufficient for a save/checkpoint operation.

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