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 this thoroughly by explaining access levels, the preview limitation, unlock_url pricing, row masking, processing time, and the polling behavior. It also reveals the 'full' vs 'preview' distinction based on API key credit, which is essential for setting expectations.

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 dense but well-structured: the core purpose is front-loaded, and subsequent sentences cover return behavior, limitations, pricing, and polling. It is longer than average, but every clause carries meaningful operational information, so the length is justified.

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 there is no output schema, the description does an excellent job of explaining the return values (session_id, access.level, unlock_url, status) and the asynchronous behavior. It also covers edge cases like large statements and password-protected PDFs. An agent has enough contextual information to invoke the tool and handle the response 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 description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by enumerating the accepted file formats (PDF, CSV, XLS, XLSX, OFX), clarifying that content is base64, and tying the password parameter to locked PDFs. This is useful supplement rather than duplication.

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 ('Upload a bank statement ... and run AI extraction + categorisation'), names the resource and supported formats, and clearly differentiates this tool from siblings by making its role as the upload/extraction entry point obvious. It is immediately clear what the tool does and how it relates to get_job.

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 description gives clear guidance on when to use the tool: to upload a statement and start extraction. It also provides a conditional alternative: if status is 'processing', poll get_job. It does not explicitly mention get_transactions, but the primary usage context and the relationship to get_job are well covered.

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