set_sleep_settings

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

With no annotations, the description carries the full burden and does so unusually well: it discloses that a new idle_timeout recreates only the socat container, that the app is briefly unreachable, that it applies to the next request's Sablier session, and that deep_sleep_after applies immediately. It omits reversibility, permission/auth requirements, and error behavior, so not a 5.

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?

Front-loaded with the purpose, then dense but relevant detail in a single paragraph, closing with the HTTP verb for context. Every sentence carries information; only the bare 'HTTP PATCH /sandboxes/{name}' line is arguably redundant padding.

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 tool with no annotations and no output schema, the description covers the side effects and rollback implications of each parameter well. It is missing auth/permission expectations (e.g. who may change disk), return behavior, and error cases, so it is strong but not complete.

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 only 25%, so the description must compensate. It adds genuine meaning for idle_timeout and deep_sleep_after (timing of when each takes effect), while 'name' is implied by 'existing sandbox' and 'disk' is left entirely to the schema's single admin-only note. Partial compensation, so 3.

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 ('Change sleep settings') and immediately names the exact fields mutated ('idle_timeout and/or deep_sleep_after of an existing sandbox'), which distinguishes it from the action-oriented siblings sleep_sandbox and deep_sleep_sandbox. The differentiation from those siblings is only implicit, though, so it falls short of a 5.

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 implies usage (configure timeouts on an existing sandbox) but never states when to call this instead of sleep_sandbox/deep_sleep_sandbox, what happens if the sandbox doesn't exist, or whether permissions are required. No explicit alternatives or exclusions are given.

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