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

Annotations provide openWorldHint=false and destructiveHint=false but no readOnlyHint, so the description carries the burden of explaining the write behavior. It does so: the call mutates an existing app's selector/display, and "publish=true to make it the live manifest immediately" implies the previous version is superseded. This adds useful behavioral context beyond the structured annotations, though it stops short of spelling out the fate of the previously live version.

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 with zero filler. The core purpose is front-loaded in the first sentence, the authoring workflow in the second, and the sibling disambiguation in the third. Every sentence earns its place, and the parenthetical about create_app is placed exactly where the agent needs it.

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?

Given the tool's complexity — versioning semantics, publish behavior, a nested definition object, and an output schema — the description covers the essentials: purpose, definition authoring path (get_app_definition_schema), publish mechanics, and alternative routing. Minor gaps remain (whether the prior live version is destroyed or demoted on publish, and how unpublished drafts are listed), but nothing that would block a correct call.

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 schema already documents app_id, publish, and definition thoroughly. The description adds modest extra framing — "membership selector (prefix rules, includes/excludes)" gives the definition parameter practical meaning, and "live manifest" sharpens the publish semantics. This is value-add but not substantial enough to push above baseline.

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 names a specific verb and resource — "add a new version to an EXISTING app (by app_id)" — and states exactly what the version changes: "membership selector (prefix rules, includes/excludes) or display." It explicitly distinguishes itself from the immediate sibling create_app ("For a brand-new app, use create_app"), and is also distinguishable from the other create_*_version siblings by naming its resource.

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 an explicit when-not with a named alternative: "(For a brand-new app, use create_app.)" It also gives workflow guidance for the main path — author the version definition against the schema fetched from get_app_definition_schema — and explains when to set publish=true versus leaving the draft unpublished. The agent can select and execute this tool without inference.

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