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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description goes well beyond that by disclosing hard limits, the 300-second upload window, the requirement to PUT bytes with matching Content-Type and Content-Length, and 30-day deletion of the import and file. The returned status ('awaiting_upload'), uploadUrl and uploadExpiresAt are also named, which is exactly the two-phase behavior an agent must know.

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?

Dense but every clause carries information: limits, parameters, return shape, upload procedure, retention, and usage condition. Minor weakness is that the 'Use when' selector is placed last rather than front-loaded, and the MIME type is spelled out in full mid-sentence, which lengthens an otherwise tight paragraph.

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 non-idempotent mutation with an output schema, the description covers everything an agent needs to invoke it correctly: required inputs, size limits, the signed-URL upload contract with headers and timeout, and the follow-up tool. Return values are summarized rather than duplicated from the output schema, which is appropriate.

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 only 33%, so the description has to carry weight: it names all three required parameters and clarifies that sizeBytes must be the file's exact size while contentType is restricted to the two enumerated MIME values. It partly restates the enum and the schema's own 'exact size' note, and adds nothing to fileName, which keeps it below a 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?

States a specific verb and resource ('Start importing a CSV or .xlsx file') and immediately bounds the scope with concrete limits (5 MB, 10 sheets, 2,000 rows/sheet, 5,000 total). An agent can distinguish this from getImport/commitImport because the description positions it as the first step of an upload-then-getImport workflow.

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?

Ends with an explicit 'Use when: the user has a spreadsheet of things to test and you can upload it', which is real when-to-use guidance. It also describes the downstream step ('then call getImport'), though it does not explicitly exclude any alternative or state prerequisites such as auth scope.

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