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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description is consistent with all three. It goes well beyond them by disclosing the auth model (Bearer API key, no anonymous execution), the payment semantics of x402 vs prepaid credits, the recovery rule (reuse the SAME idempotency_key and inputs rather than starting a new job), and the async admission-vs-delivery distinction with SHA256 verification. The only thing keeping it from a 5 is that failure/partial-success behavior and output location are stated only by reference to sibling tools.

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 core action and ordering guarantee, then alternatives, then auth/async mechanics. Every sentence carries information, though the payment-mode and idempotency sentences partially duplicate what the schema's own field descriptions already say, making the block slightly denser than strictly necessary.

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 nested-input, async, authenticated mutation with no output schema, the definition covers everything an agent needs: the ordering contract, the alternative tools, auth and payment requirements, the retry protocol, and the exact follow-up tools (skavio_agent_job_status, skavio_agent_job_result) plus SHA256 verification for retrieving the result.

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 earns extra credit by adding real semantics: the inputs are ordered so concatenation order is caller-controlled, the 2-to-5 range is a hard contract rather than a convention, and retries must reuse the idempotency_key with identical inputs. It does not elaborate on the legacy 'units' field or the size limit, which the schema already covers.

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 concrete verb and resource ('Combine two to five uploaded base64-encoded PDF documents into one output document') plus a meaningful constraint ('preserving the supplied order'). It explicitly distinguishes itself from pdf_split and pdf_to_text, so an agent can route 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?

Names the exact condition for use ('Use to concatenate files') and the two alternatives with their distinct purposes ('pdf_split to select pages from one PDF', 'pdf_to_text to extract text'). It also supplies the operational precondition chain: authenticate, submit, then poll and retrieve rather than waiting for synchronous delivery.

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