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

Annotations establish this is a non-read-only, non-destructive, closed-world write, but the description does not add the context an agent needs: what is actually being written, whether it overwrites an existing target, whether the export must exist beforehand, or what happens on size violation. 'Storage upload target' is a label, not a behavior.

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 text is short with no filler, and the 'Widget only' qualifier is front-loaded. However, it is a noun phrase rather than a structured statement, and its brevity comes from omission rather than discipline.

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?

A two-required-parameter write tool with zero schema description coverage, no output schema, and a one-line fragment is not sufficiently specified. An agent has no basis for constructing a correct call beyond guessing from parameter names.

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 0% for two required parameters, so the description carries the full burden and supplies nothing. Crucially, it does not explain that 'bytes' is an integer bound at 524288000 — an agent cannot tell whether this is a payload, a byte count, or an offset — and 'exportId' is left entirely undefined.

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 is effectively a rephrasing of the tool name: 'upload_local_export' becomes 'storage upload target'. It adds two fragments of information ('Widget only', 'browser-rendered MP4') but never states the operation as a verb+resource, and it does not distinguish this tool from begin_local_export or finish_local_export, whose sequencing it clearly participates in.

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?

'Widget only' is a scoping constraint, not usage guidance. There is no statement of when this tool is required versus begin_local_export/finish_local_export, no precondition that an export must be begun first, and no exclusion of other export paths such as export_video or export_hd_video.

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