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

Annotations already declare non-read-only, non-idempotent, non-destructive behavior. The description adds important context beyond them: anonymous jobs without a KP API key, free preview, pay-per-job for final output, and 7-day data deletion, which materially affects whether an agent should start a job.

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 front-loaded with the core action and workflow, and each sentence contributes input types, file delivery, return value, or pricing/auth behavior. The long list of file formats is dense but appropriate, and there is no filler.

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 complex 8-parameter upload tool with nested file objects and no output schema, the description covers the essential entry-point workflow, file input modes, job_token return, default target, and anonymous-job behavior. It leaves minor gaps such as the 20-file limit and duplicate handling to the schema, which is acceptable.

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 75%, so the schema already documents most parameters. The description adds useful context for file delivery via content_base64 or https URL, the job_token, and the default DATEV target, but it does not explain chart, language, client_number, or force_duplicate beyond the schema.

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 states a specific action (start a conversion job or add files with job_token), the exact input types (German bank statements and payment-provider reports), and the output targets. It is immediately distinguishable from siblings such as get_job_status and download_result, which are downstream consumers of the job_token.

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?

It implicitly positions itself as the entry point by saying it returns a job_token for all further tools, and explicitly distinguishes starting a job from adding files to an existing job. It does not name sibling alternatives or state when not to use it, but the workflow context is clear.

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