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

Goes well beyond annotations by disclosing 10 MB per-file limits, tier quotas (Starter 5 docs/50k tokens, Pro 100/500k), text extraction at upload with search on every call, and a 24-hour dedup window. The dedup and non-removal statements are consistent with idempotentHint=true and destructiveHint=false. It stops short of saying what happens on duplicate fileName or how a failed extraction surfaces.

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 onboarding step and the action, then layers format, limits, and idempotency in a logical order with no filler. It is dense to the point of being a single run-on block, which slightly hurts scanability.

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 mutation tool with no output schema and only 40% schema coverage, the description should say what the call returns (document id, extraction status) and clarify contentType. It compensates well on input mechanics and limits, but an agent still cannot predict the response shape or the failure modes of a partial upload.

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?

With schema coverage at 40%, the description carries meaningful weight: it explains contentBase64 as raw file bytes base64-encoded and that fileName's extension selects the document type. However, contentType is never mentioned in either schema or description, and businessId is only covered by the schema itself, leaving a real gap among the five parameters.

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 ('Upload a document the receptionist should answer from') and enumerates the document kinds (menu, price list, policies, manual). It also implicitly distinguishes itself from the website-import siblings by noting 'a website import never removes uploads', so an agent can tell which knowledge-ingestion tool to pick.

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?

Gives clear context for use (feeding the receptionist's answer corpus) plus concrete operational rules: supported extensions, PDF/DOCX server gating, tier limits via get_knowledge_usage, and when to mint a new idempotencyKey. It does not explicitly exclude alternatives such as put_knowledge/patch_knowledge or start_knowledge_import, so the sibling routing is only partially spelled out.

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