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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive, closed-world write. The description's added value is the caller context — that the UI card, not an agent, invokes it — which is genuinely useful. It says nothing about auth requirements, failure modes, or what the token lifecycle does after upload.

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?

Two short sentences with zero waste; the prohibition and the redirect are front-loaded where an agent will read them first.

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?

An output schema exists, so return values need no explanation, and the description covers who calls the tool and what to do instead. It is complete for routing purposes, with only minor behavioral detail (token semantics, failure handling) left uncovered.

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 token, filename, and data_base64 are already documented in the schema, including the note that data_base64 accepts base64 or a data: URL. The description adds no format or constraint detail beyond that, so the baseline 3 applies.

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 states a concrete action and its origin: it hands over an image the user picked from the iMario card in chat. That is specific enough to separate it from the general upload path, though it never states the verb+resource in a canonical form like 'upload an image asset to the store'.

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?

It gives an explicit exclusion ('Agents: do not call this') and names the correct alternative plus the mechanism ('use request_upload and send the file to its upload_url instead'). Nothing about routing is left to inference.

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