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

With only minimal annotations (readOnlyHint=false, destructiveHint=false), the description carries the behavioral burden and exceeds it: it discloses the 16 MB branching behavior, the fallback when multipart creation fails, the exact response shape in each branch, the prerequisite contact-email requirement, and the post-upload ETag reporting step. Nothing contradicts the 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?

The description is dense but every sentence carries distinct information: purpose, prerequisite, body shape, threshold behavior, follow-up, fallback, scope. It is front-loaded with the core purpose and remains compact given the branching complexity it must explain. A slightly more structured layout (e.g., separating thresholds from follow-up) would earn a 5.

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?

There is no output schema, so the description must convey return values, and it does: it names `multipart` (with upload_id, part_size, presigned PUT per part) and `upload`, plus the fallback behavior. It covers prerequisites, scope, and follow-up. Minor gaps remain: the contents of the single `upload` response are unspecified, and the optionality of `size` in the schema vs its prominence in the description is unaddressed.

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 genuine meaning above the schema by explaining that size drives the single-vs-multipart decision at the 16 MB threshold, and it restates the body shape. It does not however clarify why size is optional in the schema while the body example lists it, so it stops short of 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?

The description identifies a specific resource and mechanism: 'Presigned upload for the walkthrough video.' This clearly states what the tool produces and for which asset, going well beyond a restatement of the name. It doesn't explicitly contrast itself with the sibling complete_upload or hand_off_video, so it stops short of full sibling differentiation.

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 a prerequisite ('Requires stored contact email'), an auth scope ('jobs:write'), and a clear threshold rule for when multipart vs single upload applies. It also points to the follow-up action ('Report each part's ETag to /upload-complete'). However, it never explicitly states when to use this tool versus an alternative or when not to use it; usage context is strong but exclusions/alternatives are only implied.

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