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

Beyond the annotations, the description discloses important runtime behavior: zero-downtime rolling update for apps without storage, and a stopped/started cycle with temporary unreachability for apps with storage. This is valuable operational context an agent could not infer from the schema or annotations. No contradiction with annotations exists.

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 with no filler. The purpose is front-loaded, the when-to-use is immediate, the key constraint is stated, and the behavioral caveat is last. Every sentence earns its place.

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 mutation tool with no output schema, this description covers purpose, trigger conditions, parameter constraints, prerequisite steps, and runtime effects. Nothing essential is missing for an agent to select and invoke the tool 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. The description adds extra meaning by clarifying that the new size must fit the available compute pool and that get_resource_usage should be called first, going slightly beyond the schema's mention of valid values.

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 how much memory one app gets.' It clearly focuses on a single app's memory, distinguishing it from sibling tools like resize_database and resize_database_storage.

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?

Explicitly says when to call it: when an app is running out of memory (OOM) or the user asks to make an app bigger or smaller. It also gives a strong prerequisite: call get_resource_usage first to verify the new size fits the compute pool. It does not explicitly name alternative sibling tools, but the app-vs-database distinction is clear enough.

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