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

With no annotations, the description carries the full disclosure burden, and it does surface one non-obvious consequence: omitting tester_emails leaves ASC showing 0 Testers and TestFlight empty. It also flags the "VALID build" prerequisite. But for a 17-parameter mutation it says nothing about beta review gating (skip_beta_review), whether external groups require review, or what side effects/notifications occur.

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 sentences, front-loaded with the core action and the pitfall second. Dense but readable, and no sentence is filler. The second sentence's phrasing ("or call invite_testflight_testers testing_scope=internal") is slightly compressed but still parseable.

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 17-parameter tool with no annotations and no output schema, the description is far too thin: build selection logic, beta review behavior, and the majority of beta_* parameters are undocumented anywhere. An agent could call it, but would likely misuse build_selection or skip_beta_review without trial and error.

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 12%, so the description must compensate and largely does not. It clarifies tester_emails (ASC team addresses) and the internal/external meaning of testing_scope, but leaves build_id vs build_number vs build_selection=latest, beta_group_name, skip_beta_review, and the six beta_* metadata fields entirely unexplained.

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 ("Add a VALID build to TestFlight internal or external beta group") and immediately distinguishes the internal vs external paths. It names the sibling invite_testflight_testers, so an agent can route between them, though it never clarifies how this relates to submit_testflight_beta_review or set_version_build.

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?

Gives an explicit conditional: for internal distribution, either pass tester_emails or call invite_testflight_testers with testing_scope=internal. That is real when-to-use guidance tied to a named alternative. It stops short of saying when external distribution is appropriate or whether beta review must precede it.

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