promote_android

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

With no annotations, the description carries the full burden and does well on the highest-risk trait: without confirm=true it only validates and publishes nothing, which prevents accidental production deploys. It also explains staged-rollout semantics for sub-1 values. It omits auth/permission requirements, whether an existing production release is replaced, and whether the promotion can be halted after the fact.

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 tight sentences, front-loaded with the action, then the rollout rule, then the safety gate. No filler and no repetition of schema structure.

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?

The output schema covers return values and the description covers the dry-run gate, so the core is present. But for a 7-parameter production-mutation tool with zero annotations and zero schema descriptions, missing notes on the source-track default, locale default, and permission/irreversibility leave the agent short of fully safe invocation.

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 coverage is 0%, so the description must compensate and it only partially does. It gives real semantics for confirm, rollout, and release_notes, and 'given Play language code' implicitly explains locale, but from_track (defaulting to internal), the non-obvious locale default of pt-BR, and the exact meaning of package_name/version_code are left to inference.

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 with scope: promoting a version code from a Play test track to production. This is distinguishable from upload_android (which pushes artifacts) and update_rollout_android (which adjusts an existing rollout), though it never names a sibling explicitly.

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?

Usage is implied rather than stated: the confirm=true gate tells the agent a dry-run pass comes first, and 'a rollout below 1 starts a staged rollout' hints at when to use partial rollout. There is no explicit statement of when to prefer update_rollout_android instead of a fresh promotion, nor any prerequisite about the version already existing on the source track.

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