get_text

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention side effects (though likely none), permissions, return format, or any constraints like requiring an active document. It simply says 'reads text' without elaborating on what happens for each target or whether the operation is safe.

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 a single sentence and is concise, but it includes an inaccurate reference to 'paragraphs' which is not a target option, and it omits the 'document' and 'selection' targets present in the enum. Still, it is front-loaded with the main action and resource, making it reasonably efficient.

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?

Given the tool has multiple targets and no annotations or output schema, the description is minimal. The schema provides parameter details, but the description does not clarify how the tool behaves with each target (e.g., what happens when target=frame with no frameIndex, or how selection is determined). It is functional but leaves the agent to infer details from schema and sibling infos.

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%, and each parameter (target, page, frameIndex) has its own description in the schema. The tool description adds the word 'paragraphs' which does not correspond to any enum value, but otherwise provides no additional meaning beyond the schema. Baseline 3 is appropriate since the schema already documents parameters thoroughly.

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 reads text and lists some target types (frames, paragraphs, pages) with a specific verb 'reads'. However, the target enum in the schema includes 'selection', 'document', and 'frame' – 'paragraphs' is not an option, and 'document' and 'selection' are omitted from the description, creating slight misalignment. It still distinguishes from write tools like insert_text and replace_text.

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 on when to use this tool versus siblings like list_frames or get_document_info. There is no explicit mention of prerequisites, alternatives, or conditions for selecting a specific target. The description only implies a read operation without context on when it is the best choice.

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