Start Agent Sandbox

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

Annotations only declare destructiveHint=false and openWorldHint=false; the description adds far more — copy-on-write semantics (live content never modified), a precise list of what is blocked (publishing, deleting, bulk ops, search/replace-execute), the required human review/merge at /cm/forks, and which tools behave differently inside the sandbox. This is exactly the extra context the annotations leave out.

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?

Purpose is front-loaded in the first sentence, followed by a scannable bullet list of behavioral consequences and a closing call to action. No sentence is redundant; every bullet conveys a distinct, actionable constraint.

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 session-lifecycle tool with no output schema, the description covers initiation, in-session semantics, blocked operations, safety guarantees, and teardown. Nothing an agent needs to invoke it safely and correctly appears to be missing.

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 description coverage is 100%, so both the 'name' and 'description' parameters are already fully documented in the schema (including the auto-generation behavior when 'name' is omitted). The description adds no parameter-level detail, so the baseline of 3 applies.

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 and resource: 'Start a sandboxed editing session backed by a content fork.' The parenthetical 'pull request for content' and the explicit copy-on-write behavior clearly separate it from siblings like create_fork, fork_page, and end_agent_sandbox.

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?

'Recommended for any multi-page or risky editing task. End with end_agent_sandbox.' gives a clear when-to-use condition and names the companion teardown tool. It stops short of naming when NOT to use it (e.g., single-page edits vs. create_fork), so it falls just short of a 5.

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