node_clear_script_errors

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

With no annotations, the description carries the full burden and discloses the main behaviors: clearing the accumulated log, forcing a cook, and re-reading errors. It also explains the force_cook option meaning, which is useful. It could mention return shape or permissions, but these are minor for this operation.

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 compact and front-loaded with the core action, then gives a useful interpretation rule, then documents parameters. It is slightly redundant because the opening sentence already says force a cook and the force_cook line repeats it, but there is no fluff.

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 two-parameter mutation tool with no output schema and no annotations, this is reasonably complete. It tells the agent what will happen, what the optional parameter controls, and how to interpret one-off versus recurring errors. Explicit return-value or confirmation behavior would be the only notable gap.

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?

The description adds meaning to both parameters beyond the bare schema: path is the operator path, and force_cook controls the post-clear cook(force=True) behavior. There is a minor mismatch where the prose says the default is true while the schema says null, but the description still meaningfully compensates for the 0% schema coverage.

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 a specific action: clear a node's accumulated script-error log, then force a cook and re-read. This makes it clearly distinguishable from sibling read tools like node_errors and node_errors_deep.

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 recurring-vs-one-off explanation provides a concrete decision heuristic: recurring errors indicate a live problem, while one-off hits are stale. It does not name alternatives such as node_errors explicitly, so it is not a perfect 5, but the context is otherwise clear.

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