get_item_annotations

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

With no annotations provided, the description carries the full burden. It discloses the output scope (all annotations, reading order) and the value proposition, but it does not mention whether this is a read-only operation, whether it requires specific permissions, whether it can fail (e.g., item has no PDF), or whether it returns an empty list. It is not misleading, but it leaves some behavioral gaps.

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 two sentences, front-loads the core action and output, and the second sentence adds a valuable use-case rationale without bloat. Every sentence earns its place.

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 single-parameter read tool with no output schema, the description is quite complete: it lists the output fields, ordering, and the use case. It lacks explicit failure/edge-case behavior (e.g., no PDF, no annotations) and does not name sibling tools, but given the low complexity, it is nearly 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%, so the description must compensate. It explains what item_key refers to implicitly ('an item's PDF') but does not define item_key format, how to obtain it, or any constraints. The description adds context about the item's PDF but the parameter itself is only documented by its name and type. Baseline 3 is appropriate because the single parameter is self-explanatory in context.

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 uses a specific verb ('Get') and resource ('every PDF annotation on an item's PDF'), enumerates the annotation types (highlights, notes, underlines) and the exact data returned (highlighted text, comment, color, page label, reading order). It clearly distinguishes itself from siblings like get_item_fulltext and get_item_notes by focusing on user annotations rather than raw text or notes.

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 when to use it: when the user's annotations are more useful for synthesis than raw PDF text. It contrasts with raw PDF text, which helps an agent choose between this and get_item_fulltext. However, it does not explicitly name sibling alternatives or state when not to use it, 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.