herdr_owned_pane_close

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the checks performed (identity, state, cursor, controller, checkpoint) and explicitly states that files, worktrees, and branches are preserved, which is valuable. However, it does not disclose what happens to the pane itself beyond 'close' (e.g., whether it is deleted, returned as a result), nor any side effects or error conditions. It adds some context beyond the schema but lacks critical details for a destructive-looking 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 a single sentence that is relatively concise and front-loads the primary action ('Capture and close'). It uses dense technical jargon but does not waste words. The structure is straightforward, though the list of checks is compressed into a stream of terms that could be parsed more cleanly. Overall, it is appropriately short for the information it conveys.

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 8 parameters (7 required), no annotations, no output schema, and a complex domain, the description is insufficiently complete. It does not explain the return value, error handling, or the meaning of 'capture.' It mentions preservation of files/worktrees/branches but not what happens to the pane itself. Given the complexity of the operation, an agent would need additional documentation or schema descriptions to use it safely and correctly.

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 schema has zero description coverage for its 8 parameters, so the description must compensate by explaining their meanings. The description mentions vague groupings like 'exact identity, idle/done state, fresh state cursor, controller, and durable checkpoint checks' which may correspond to parameters but does not map them explicitly. It fails to clarify what lease_id, controller_id, checkpoint_ref, etc. actually represent or how they should be filled. An agent reading the description would not know what each parameter needs or why, making correct invocation difficult.

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: close a pane, specifically a cleanup-only adopted pane, and mentions preservation of files/worktrees/branches. It distinguishes itself from siblings by specifying 'cleanup-only adopted pane' and the checks performed. The verb 'capture' is somewhat ambiguous, and it doesn't explicitly name the resource type in the same way a simpler definition would, but the core purpose is clear.

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 provides no explicit guidance on when to use this tool versus alternatives. It mentions 'cleanup-only adopted pane' which hints at a use case, but there is no comparison to sibling tools like herdr_owned_reviewer_close or herdr_owned_worker_release, and no conditions for when this is the right choice. The agent must infer from the name and the 'cleanup-only' phrase, which is insufficient for a tool with many siblings.

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