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

Annotations only declare the basic safety profile (readOnly=false, destructive=false, openWorld=false). The description goes well beyond: ingestion runs in the BACKGROUND and returns a runId, embedding spends workspace inference credit, and the call sits behind an approval gate that may return a needs_confirmation envelope. This is exactly the extra behavioral context an agent needs.

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?

Front-loaded with the core action and ingestion behavior, then constraints and routing. It is dense and somewhat long, but nearly every clause carries operational value (limits, encoding, background semantics, credit spend); the density is justified rather than padding.

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 output schema, the description still closes the loop by explaining that the result carries a runId, how to check it, and the possible needs_confirmation envelope. Combined with the limits and encoding rules, an agent has everything required to invoke it correctly.

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 the baseline is 3, but the description adds real meaning: text goes inline as Markdown/plain text/CSV in utf8, binary files go base64-encoded with their mimeType, and it restates the 50-source / ~10 MB limits. It also points to <attached-file> blocks as ideal source material.

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?

States a specific verb and resource ('Adds documents to a knowledge base and starts ingestion') and immediately differentiates by ingestion mode (text vs binary vs graph vs tabular). It also names the sibling tools it interacts with, so an agent can place it against workbench_kb_search and workbench_kb_documents_list without opening schemas.

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?

Explicit when/when-not guidance and alternatives: check workbench_kb_documents_list first to avoid duplicates, use workbench_kb_ingestion_status to check progress and explicitly 'don't poll', and workbench_kb_search only works once ingestion finishes. Names the approval gate as a condition that may return needs_confirmation.

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