wait_for_annotations

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It meticulously explains the blocking behavior, the timeout status as non-error, the retry protocol, and the detailed structure of each returned annotation (kind, note, geometry_svg, hits, texts_in_region). It also clarifies that timeout is not an error and how to proceed. This is exceptionally transparent for a wait operation.

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?

The description is well-organized: it opens with the core purpose and immediate return, then clearly explains the timeout protocol, and finally lists the annotation fields. Every sentence serves a purpose, with no redundant phrasing. It is concise yet comprehensive, front-loading the most important behavioral information.

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?

The description is thorough for a wait tool: it covers the blocking behavior, timeout handling, retry instructions, and the full return payload structure. It does not describe error scenarios (e.g., if the session expires) or what happens if the user submits invalid annotations, but given that there is no output schema and the tool is relatively simple, the provided details are largely sufficient. A small gap prevents a perfect score.

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?

The schema has 0% description coverage for the single parameter timeout_s (default 120), and the description does not explicitly explain this parameter. However, the description mentions status='timeout' and the retry protocol, which implies that the tool waits for a specified period. This indirect inference is not as clear as explicitly stating 'timeout_s is the maximum wait time in seconds.' The description adds some context but doesn't fully compensate for the lack of schema detail, so a 3 is appropriate.

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 tool's purpose: '阻塞等待用户在浏览器里提交批注' (blocks waiting for user annotations) and that it returns the annotation content immediately upon submission. It identifies the specific verb 'wait' and the resource 'annotations', making it distinct from siblings like get_annotations (which likely retrieves existing annotations) and open_svg. However, it doesn't explicitly name a sibling alternative, so it stops 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 provides explicit instructions on when to use this tool: it should be called when waiting for user annotations, and if status='timeout', it should be called again to continue waiting. It also defines a clear stopping condition: until status='submitted' or the user explicitly declines to annotate. It doesn't discuss when not to use it relative to siblings, but the protocol is sufficient for correct usage.

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