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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses the key non-obvious behaviors: the update creates a new version, preserves existing data and settings, updates the open screen immediately, leaves the running version untouched on validation failure, and is logged to device_log with old and new versions. This is exactly the context an agent needs before mutating a live app.

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?

Four sentences, front-loaded with the core action, then semantics, then failure modes, then audit trail – no filler. A couple of sentences are dense and run-on ('A spec with problems comes back with each problem's path and a fix, and the running version is not touched'), but nothing is wasted.

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 mutation tool with a nested spec object, no output schema, and four parameters, the description covers versioning semantics, success side effects, error codes, and logging. There is no meaningful gap left for an agent calling it correctly.

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 100%, so the baseline is 3, but the description adds real meaning by indicating the spec is a complete replacement ('giving its new spec', echoed by 'The whole new spec' in the schema) and by describing how problem paths are reported back. The 'name' parameter is not mentioned, but the schema documents it adequately.

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 ('Change an app') and anchors it to the sibling that produces the resource ('made with create_app'), making the create-vs-update distinction explicit. An agent can identify the tool 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?

It clearly scopes use to apps that already exist ('made with create_app'), which implicitly routes new-app creation elsewhere. It stops short of an explicit 'do not use for new apps, use create_app instead' exclusion, so a small inference is left to the agent.

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