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

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true. The description goes well beyond that: it discloses that the call consumes the caller's Klippa credits, that pricing is per request or per page with extra components adding cost, that free credit starts at EUR 25, that the artifact lands in Doxis AI.dp storage as a file id, and it exposes the endpoint path. This is exactly the cost/side-effect context an agent cannot get from annotations.

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?

Dense but well front-loaded: the merge action and the credit warning lead, followed by output location and input forms. The billing tangent ('Billing → Pricing in the platform'); 'EUR 25 of free credit') is slightly verbose, but it is decision-relevant and the whole block stays compact with no filler sentences.

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 carries the return-value burden and does so ('returned as a file id'), while also covering storage location, cost model, accepted input forms, ordering constraint, and endpoint. For a single-parameter tool with a rich nested schema, nothing an agent needs to call it correctly 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 description coverage is 100%, so the baseline is 3, but the description adds real meaning the schema does not express: each document is one of url, data_base64 or file_id (the schema lists all three properties without an exclusive oneOf), documents must be given in merge order, and page_ranges is optional with a default of all pages. Minor gain over a fully documented schema, hence a 4 rather than 5.

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 ('merge two or more PDFs into one'), plus scope details: order preserved, optional per-document page subsetting, and the output ('stored in Doxis AI.dp storage and returned as a file id'). An agent can distinguish this from dochorizon_document_split and dochorizon_upload_file 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?

Usage is implied by the verb plus the cost framing, and the description gives a useful deployment condition (credit consumption, billing per request or per page). It never states when NOT to use this tool or names a sibling alternative (e.g., document_split) that an agent should prefer for the inverse operation, so the guidance stays implicit rather than explicit.

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