get_annotations

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

The description suggests annotations can be retrieved for the entire document or a specific node, but the input schema requires nodeId, implying only node-specific retrieval. This is misleading. No additional behavior is disclosed, such as return format, pagination, or error conditions. With no annotations provided, the description carries full transparency burden and fails to provide accurate details.

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 one short sentence and is efficient. However, the phrasing 'current document or specific node' introduces ambiguity that could have been avoided, making it slightly less precise but still concise.

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?

With no annotations, no output schema, and a simple parameter list, the description should be more complete. The misleading scope ('current document') and lack of any detail about return values or edge cases leave significant gaps. The tool is not adequately specified for an agent to use confidently.

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 coverage is 100%, so baseline is 3. However, the description adds confusion about the required nodeId by mentioning 'current document' as an option, which contradicts the schema's required field. It also does not clarify the includeCategories parameter, providing no additional value.

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 gets annotations, with a specific verb ('Get'), resource ('annotations'), and scope ('current document or specific node'). It distinguishes itself from sibling tools like set_annotation and set_multiple_annotations, which are write operations.

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 intended use is implied: use this tool to retrieve annotations. No explicit guidance is given about when to use this versus other get tools (e.g., get_node_info) or set tools. There is no mention of exclusions or alternatives.

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