computer_continue

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

Annotations already indicate destructiveHint=true (potential side effects) and readOnlyHint=false. The description adds context that it keeps the same 'apps, observed memory, and success conditions' and returns a new task ID, which is useful. However, it does not disclose the destructive nature explicitly, relying on annotations. There is no contradiction, so a score of 3 is appropriate—description adds some behavioral context but not the full safety profile.

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 sentences with no fluff. The key action and purpose are front-loaded, followed by behavioral context and the result (new task ID). Every sentence serves a purpose: what it does, what it preserves, and what it returns. Excellent structure.

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 moderate complexity (3 params, nested object, no output schema), the description covers the essential purpose, context preservation, and the returned task ID. It could provide more details on how to structure 'inputs' or 'guidance', but the description is sufficient for an agent to understand the tool's role. Given the annotations and schema, it is fairly 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 description coverage is 0%, meaning the description must compensate for undocumented parameters. The description explains taskId implicitly ('continues a task') and mentions 'additional guidance' which aligns with 'guidance' parameter. 'inputs' is not mentioned explicitly but is implied by 'missing text values'. Baseline is 3 due to low coverage, and the description does add some meaning, but not comprehensive for all three parameters.

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 verb 'continue' and the resource 'an unfinished stopped task', distinguishing it from a generic new task. It mentions preserving context (apps, memory, success conditions) and observing fresh state, which helps differentiate from sibling tools like computer_act or computer_run that likely start new actions. However, it could more explicitly contrast with siblings for higher clarity.

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 this tool is for continuing a previously stopped task, which is a clear context. It does not explicitly state when NOT to use it or name alternatives like computer_act for starting new actions. The absence of explicit exclusions is a minor gap, but the purpose is clear enough for an agent to infer intended usage.

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