readOfficeDoc

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

With no annotations, the description carries the behavioral burden. It discloses that the document is converted from PDF to text, which is a notable behavior, and 'retrieves' implies a read-only operation. However, it lacks details about error handling, size limits, authentication, or the exact text output structure, leaving gaps that a more thorough description could fill.

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, well-structured sentence with no wasted words. It immediately states the verb ('Retrieves'), the object ('content'), and a key qualifier ('converted from PDF'), making it concise and front-loaded.

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 simple tool with one parameter and no output schema, the description provides sufficient context: it specifies what is returned (text), the source conversion step, and the required ID. However, it could be more complete by mentioning potential issues (e.g., unsupported file types, formatting loss) or clarifying the output structure in more detail, but this is a minor gap for such a straightforward operation.

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?

The input schema already describes docId as 'ID of the Office document to read,' and the description reinforces this. With schema coverage at 100%, the description adds minimal new parameter meaning—only 'specific' and the conversion note, which do not substantially change how the parameter should be used. Thus, the baseline 3 is appropriate.

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 a specific action ('Retrieves the content') on a specific resource ('a specific Office document') and includes a distinctive detail ('converted from PDF'). This distinguishes it from sibling tools like listOfficeDocs, searchOfficeDocs, and readGoogleDoc, which manage or retrieve other document types.

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 context is clear: use when you have the docId and need the text content of an Office document. It implies the need for an ID, and the mention of 'converted from PDF' hints at the output format. However, it does not explicitly mention alternatives (e.g., listOfficeDocs to find IDs) or when not to use this tool.

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