End Agent Sandbox

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

Annotations only give a blanket destructiveHint=true; the description resolves that ambiguity by specifying that 'discard' permanently deletes the fork and every change while 'submit' preserves it at /cm/forks/{id}. Disclosing the human-merge governance rule is behavior an agent cannot infer from annotations or schema.

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?

Three tight sentences, front-loaded with the purpose, then the action semantics, then the governance constraint. No filler and nothing restating the tool title.

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 single-parameter tool with no output schema, the description covers both execution paths and the policy boundary, which is nearly everything an agent needs. It does not say what the call returns or what state the session is left in after 'submit', a minor gap given no output schema exists.

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 100% and the schema already defines both enum values, so 3 is the baseline. The description nonetheless adds the fork's review location (/cm/forks/{id}) and the irreversibility contrast between the two actions, which is slightly more than the schema conveys.

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?

States a specific verb+resource ('End the sandbox session') and then unpacks the two terminal outcomes, keeping the fork for human review versus permanently deleting it. This clearly separates it from merge_fork and delete_fork, which are the nearest siblings an agent might confuse it with.

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?

Explicitly tells the agent which action to pick and why: 'submit' for human review/merge, 'discard' for permanent deletion. It also states a hard constraint (agents cannot merge their own sandbox), which is genuine when-to-use guidance. It stops short of saying when to prefer this over rollback_agent_session or get_agent_session_changes.

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