Merge documents

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses the async execution model ('Runs asynchronously — poll the returned task with get_task') and the safe-by-default behavior ('The originals stay unless delete_originals is set'). These are material behavioral traits an agent must know before invoking, and they are consistent with the annotations. It does not discuss partial-failure behavior, but the archive_fallback parameter in the schema partially covers that.

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?

Three sentences with no filler: the first states the core operation and ordering requirement, the second the safety default, the third the async contract and follow-up. Each sentence carries unique information and the main verb is front-loaded.

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 compensates by stating that a task is returned and how to follow up (get_task), which is the key missing piece. It covers purpose, ordering, safety default, and async flow. Gaps are minor: no statement of failure/partial-merge semantics and no permission prerequisites, though the destructive hint and archive_fallback schema description mitigate these.

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 clarifying the default behavior of delete_originals ('The originals stay unless delete_originals is set'), which the schema's parameter description does not state (it only describes the effect and warns it is irreversible). This resolves a real ambiguity for an agent deciding whether to pass the flag.

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 verb and resource: 'Merge several documents into one new PDF, in the order given.' It names the output format (PDF), the ordering constraint, and by implication the resource (multiple documents → one new document). This cleanly distinguishes it from sibling PDF operations like rotate_documents and edit_pdf, which modify rather than combine.

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 usage context: ordering is the caller's responsibility, originals are preserved unless the flag is set, and the operation is asynchronous so the agent should poll with get_task. It provides a direct follow-up instruction referencing a sibling tool, though it does not name explicit when-not conditions or alternatives. Since no near-equivalent merge sibling exists among the listed tools, this is clear context without exclusions.

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