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

Annotations only carry openWorldHint=false and destructiveHint=false. The description adds substantial behavioral context beyond that: the live-manifest side effect, role-based visibility with an authoritative selector, the rejection condition when membership selects nothing, and the crucial boundary that members are never promoted. No annotation contradiction; the description enriches the safety profile meaningfully.

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 sentences, each earning its place: the primary effect is front-loaded, followed by the failure condition, then the side-effect boundary. There is no filler, jargon beyond the domain concept of a manifest, or redundancy with the schema.

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 two-parameter publish operation with an output schema and safety-relevant annotations, the description covers the purpose, the behavioral effect, the validation failure mode, and what the operation does not touch (members). An agent has everything needed to decide on and correctly invoke this tool among the large publish_* sibling family.

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%, with clear descriptions for both app_id and version, so the schema already does the heavy lifting. The description reinforces that version 'make[s] the live manifest,' mirroring the schema text, but adds no new parameter-level detail. Baseline 3 is appropriate.

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 ('Publish an app version') and defines the precise effect: 'making it the live manifest (visible per role, its selector authoritative)'. It also distinguishes this operation from the many publish_* siblings by clarifying it is app-specific and manifest-only, so an agent can differentiate it without opening the schema.

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 purpose statement doubles as when-to-use guidance (make a version the live manifest), and the description gives an explicit exclusion: publishing 'promotes only its manifest — never its members, which publish independently on their own lifecycles.' It also flags a precondition ('Rejected if the version's membership selects nothing'). It stops short of naming a concrete alternative tool for member publication, so it loses the top score.

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