Get Annotations

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the behavioral detail that the item_key must be the parent item, not the attachment, which is valuable and not in the schema. It also mentions the default limit of 100. However, it doesn't disclose pagination behavior, ordering, or what happens when no annotations exist, which would be useful for a read tool.

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 compact and front-loaded with the core purpose in the first sentence. The Args section is structured and each line earns its place. The library targeting instruction is concise. Minor redundancy: 'List all highlights and annotations' could be slightly tighter, but overall it's efficient and well-organized.

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 tool has an output schema, so return values don't need to be described. The description covers the key usage nuance (parent item vs attachment), the limit default, and library targeting. For a read-only list tool with strong annotations, this is nearly complete. The only missing piece is pagination/ordering behavior, which is a minor gap given the output schema exists.

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 for all four parameters. It explains item_key (parent item, not attachment) and limit (maximum, default 100), which adds meaning beyond the schema. However, library_id and library_type are only covered by the general instruction to pass both together, which is helpful but doesn't explain their semantics (e.g., what values are valid beyond the enum for library_type). The description partially compensates but leaves gaps.

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 a specific verb ('List') and resource ('highlights and annotations on a paper's PDF'), which clearly identifies the tool's function. It distinguishes itself from sibling tools like create_annotation, update_annotation, and delete_annotation by focusing on listing/reading. However, it doesn't explicitly differentiate from list_notes or get_item_details, which could also return related content, so it's clear but not fully differentiated.

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 clear context on when to use the tool: to list annotations on a paper's PDF. It also gives explicit guidance on library targeting ('Pass both library_id and library_type to target another library; omit both to use the configured default'), which is a usage condition. It doesn't explicitly state when not to use it or name alternatives, but the context is sufficient for an agent to select it appropriately among siblings.

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