accept

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

Beyond the sparse annotations (destructiveHint=false), the description discloses several meaningful behaviors: the merge is squashed to a single commit, the task text is the default message, the delegation worktree is cleaned up afterward, and the call refuses under dirty-tree conditions. These add real operational context the annotations do not provide. The word 'clean up' sits near the line of contradicting destructiveHint=false, but since content is preserved via the merge, it is not a hard contradiction.

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?

Two compact sentences carry the core action first, the commit-message nuance second, and the critical refusal guard last. Every clause earns its place with no filler or restatement of the tool's name.

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 mutation-style operation with no output schema, the description covers the core behavior, a parameter default, a side effect (worktree cleanup), and a precondition guard. The main gaps are the semantics of id and repo_path, and what 'refuses' looks like in practice, but an agent can reasonably invoke the tool knowing it must supply a delegation id.

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%, so the description must compensate. It does explain commit_message's role (overrides task text as the message) and implies it is optional. But the required id parameter is never described as the delegation identifier, and repo_path's purpose is left entirely unexplained. Partial compensation only.

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 names a specific verb ('Merge'), a specific resource ('a delegation'), and a precise outcome: a single commit into the current branch plus worktree cleanup. This clearly distinguishes it from sibling tools like delegate, revise, discard, and status, since only accept performs the merge-and-cleanup operation.

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 workflow context (delegation lifecycle) makes the intended use implied, and the refusal condition ('Refuses if the working tree has uncommitted changes') gives a concrete when-not-to-call signal. However, it never names alternatives or explains when to prefer discard or revise over accept, leaving sibling differentiation to inference.

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