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

With annotations only covering readOnly/openWorld/idempotent flags, the description carries the real behavioral burden and does so: it discloses that credits are spent (billed per request or per page, project pricing, extra components add cost), that output images land in Doxis AI.dp storage and come back as file ids, and it even names the underlying endpoint. This is exactly the side-effect context an agent needs before calling a billable tool.

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 highest-value signal ('SPENDS CREDITS'), and most sentences carry information. The billing paragraph (project pricing, Billing → Pricing, EUR 25 free credit) is somewhat more commercial detail than an agent needs, mildly diluting density.

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?

No output schema exists, so the description must explain returns — and it does ('returned as file ids'). Combined with input-source rules, cost model, storage side effect and password/content_type hints, an agent has everything needed to invoke this correctly. Nothing material is missing.

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 a constraint the schema does not encode: the document must be supplied as exactly one of url, data_base64 or file_id (the schema lists all three as optional with no oneOf/XOR). It also restates that each render config carries page_ranges plus optional width/height, reinforcing the nesting.

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 ('render pages of a PDF as images') plus the tunable output shape (width/height), which cleanly separates it from siblings like capture_*, convert_einvoice, merge and split. An agent can identify this as the rasterization tool without opening any schema.

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 concrete usage conditions: exactly one of url / data_base64 / file_id must supply the document, and it routes to dochorizon_download_file for retrieving small results. It lacks explicit when-not-to-use guidance or comparison against adjacent siblings (e.g. document_info), so it stops short of a 5.

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