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

Annotations only declare the generic mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds the operationally important traits — accepted MIME types, an 8 MB cap, organization scoping, and a few-minute expiry. It does not say whether calling twice invalidates an earlier link or how failures should be retried, which matters given idempotentHint=false.

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, all load-bearing: sentence one names the action and targets, sentence two the return contract and format limits, sentence three the binding and lifetime. The most decision-relevant facts (signed URL, token, expiry) are 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?

For a zero-parameter staging tool with both annotations and an output schema present, the description covers everything an agent needs to call it and hand the result off: constraints, security scoping, lifetime, and the exact downstream field name. No material gap remains.

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?

There are zero input parameters, so per the baseline this dimension is largely carried by the schema and sits at 4. The description usefully documents the output contract the parameters downstream depend on (upload_token passed verbatim as reference.upload_token) rather than leaving that handoff implicit.

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+resource ('Stage an image upload for an asset reference') and enumerates the concrete asset kinds it serves (mark image, app icon, domain screenshot). It is unmistakably distinct from add_asset, which it names as the downstream consumer.

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 workflow is made explicit: this tool produces an upload_token that 'add_asset takes verbatim as reference.upload_token', so the agent knows it precedes add_asset. It never states when this step is unnecessary or what to do if an asset already has a reference, so it stops short of full when/when-not guidance.

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