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

Annotations only declare this is a non-read-only, closed-world, non-destructive operation; the description adds substantive context beyond that: no local server file reads, the receipt expiring alongside the URL, the enforced trip membership and document visibility/edit permissions, and the 25 MiB ceiling. The one weak spot is that 'The receipt expires with the upload URL' never states an actual lifetime, so an agent cannot plan around the expiry. It does not contradict the annotations, which correctly describe a write-adjacent but non-destructive preparation step.

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 action, the size cap, and the required follow-up call are front-loaded in the first two sentences, which is the right ordering. The tail is weaker: the untrusted-data sentence is generic prompt-injection boilerplate and the 'Safety: Closed-world' clause largely restates openWorldHint=false from the annotations. Neither is fatal, but both cost words without adding tool-specific signal.

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 multi-step mutation tool this covers the essentials: the ceiling, expiry, permission model, the follow-up call, and the clarification that nothing on the server is read. An output schema exists, so the description is correctly silent on return values. What is missing is any concrete expiry duration and any differentiation from the adjacent tripsy_documents_upload tool.

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 every parameter including parent_id/parent_type conditional semantics is already documented in structured form. The description reinforces the content_length ceiling and notes that trip_id access is API-enforced, but adds no new meaning for the parent_id/parent_type pairing or filename handling. Baseline 3 is the correct landing point when the schema carries the semantics.

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 first sentence names a specific verb and resource pair ('Create a private presigned S3 PUT URL and upload_token') plus a hard size limit, which is far more than a restatement of the name. It also disambiguates from the attach step by naming tripsy_documents_attach as the follow-up. It stops short of a 5 because the sibling tripsy_documents_upload sits right next to it in the namespace and is never mentioned, so an agent still has to guess which of the two upload paths to pick.

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 an explicit call order: prepare here, PUT the bytes with the returned headers, then call tripsy_documents_attach. It also states the prerequisite that owners need active Pro while permitted collaborators do not. It lacks any when-not guidance and does not contrast with tripsy_documents_upload, so the agent has no rule for choosing between the two upload tools.

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