preview_annotations

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

No annotations exist, so the description must fully disclose behavioral traits. It only states 'in-memory' (implying no persistence) and 'overlay and metadata' (implying a read operation). It does not mention whether this is a read-only operation, whether it requires special permissions, whether it modifies any state, or what the performance implications are (e.g., large overlays). The description barely scratches the surface of behavioral transparency.

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 extremely concise (one sentence, 7 words). While brevity is valuable, it is too short to convey essential information. The single sentence is front-loaded with the core action, but it lacks structure (no sections, no examples, no elaboration). Every word earns its place, but the description is under-specified for the tool's complexity.

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?

Despite an output schema existing, the description is insufficient for a tool with 7 parameters and many siblings. It does not explain what an 'overlay' is (e.g., a rendered image, a data structure), how the 'metadata' relates to the overlay, or any constraints (e.g., image format, size limits). The agent would need to rely on the output schema and parameter descriptions to infer behavior, but the high-level intent is too vague. The description is incomplete for the tool's complexity.

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% (all 7 parameters have descriptions in the schema). The tool description adds no additional meaning or context beyond the schema. For example, it does not explain how 'annotation_ids' and 'annotation_type' interact, or what 'max_width' and 'max_height' do together. Baseline score is 3 because the schema is comprehensive, but the description does not enrich the parameter semantics.

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 states 'Return an in-memory annotation overlay and metadata,' which clearly indicates a verb (Return) and resource (annotation overlay and metadata). This distinguishes it from sibling tools like 'list_annotations' (returns data) and 'preview_image' (shows raw image). However, the phrase 'overlay and metadata' is slightly vague; it could be more specific about the output format (e.g., rendered image).

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?

No guidance is provided on when to use this tool versus alternatives. Siblings include 'list_annotations', 'preview_image', and 'export_metadata_jsonl', but the description does not mention when rendering an overlay is appropriate or when to avoid it. There is no when-not, no prerequisites, and no reference to other tools, leaving the agent to infer usage from the name alone.

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