upload_build

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

Annotations already declare this as a non-read-only, destructive, open-world, non-idempotent operation. The description adds valuable operational context beyond annotations: chunk streaming, checksum commit behavior, host timeout risk for large builds, and inspecting returned reservation IDs before retrying after failure.

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 four short sentences, front-loads the core upload action, and every sentence contributes either scope, safe-usage guidance, or failure behavior. There is no redundant wording.

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 complex write tool with five parameters and no output schema, the description covers purpose, scope, and failure behavior well. However, it leaves significant gaps around the meanings of four required parameters and does not describe the successful return shape beyond referencing reservation IDs on failure.

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 20%, and only filePath is documented in the schema. The description adds some semantics for the file (signed, local, supported extensions), but it does not explain appId, version, buildNumber, or platform, leaving most required parameters without added meaning.

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 specific verb and resource: uploading a ready, signed local .ipa/.pkg/.zip via Apple's Build Upload API. It also explicitly excludes compile, sign, distribute, and submit-review behavior, which distinguishes it from siblings such as submit_for_review.

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 clearly says when to use it (a ready, signed local build), when not to use it (not for compiling, signing, distributing, or submitting review), and gives an alternative for large builds: prefer the CLI to avoid host timeouts. It also includes a retry guideline on failure.

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