upload_app_bundle

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

The description states 'Upload or replace the code' and 'Re-uploading the same version replaces it in place,' which clearly implies overwriting existing app code, a destructive operation. Yet the annotation destructiveHint is false. This is a direct contradiction, forcing a score of 1 despite the otherwise rich behavioral detail about the sandbox and SDK.

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 front-loaded with the core operation ('Upload or replace the code of an app YOU own') and every sentence earns its place by conveying constraints, storage/serving behavior, replacement semantics, and use cases. It is dense but free of filler.

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 tool with no output schema, the description thoroughly covers input constraints, sandbox behavior, SDK inlining, ownership prerequisite, and use cases. It does not mention version or content_type specifics, but the schema already documents those parameters, so the description is largely complete. Minor gaps around error cases and return values keep it from a 5.

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 meaningful constraints beyond the schema: content must be 'one self-contained entry document (HTML or JavaScript, max 512 KB, no binary)' and the app must be owned. These details help the agent understand the content parameter better than the schema alone, warranting a 4.

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 uses a specific verb and resource: 'Upload or replace the code of an app YOU own' and clearly distinguishes it from siblings by specifying it ships a new build or fixes an existing app created via create_app. It makes the tool's scope unambiguous relative to alternative tools like write_app_artifact or publish_app.

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 explicit when-to-use guidance: 'Use it to ship a new build of an app you created with create_app, or to fix one after a user reports something.' It also states the prerequisite of app ownership. However, it does not explicitly name alternatives or provide when-not-to-use exclusions beyond the implicit ownership constraint, so it falls short of a 5.

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