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

Beyond the annotations, the description discloses important behavioral details: the connection string is encrypted, stored as a secret, injected only on the next deploy, and never returned. It also notes the authentication requirement. This adds meaningful context that helps the agent predict side effects and response behavior.

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?

The description is compact and front-loads the main purpose in the first sentence. The repeated tool name at the start is slightly redundant, but the rest is efficient and every clause adds useful context about storage, encryption, deployment timing, and non-return of credentials.

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 description covers the critical operational context: what is created, where it goes, when it becomes active, and that the secret is not returned. Since there is no output schema, a bit more detail about the tool's success response or asynchronous behavior would improve completeness, but the essentials are present.

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?

The input schema already provides 100% description coverage for all three parameters, including specific guidance on engine and sessionKey. The tool description does not add new parameter-level semantics; it reinforces the engine and secret side effect but does not go beyond the schema's existing parameter documentation.

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 uses a specific verb ('Provision') and a specific resource ('managed Postgres database for an Osir app'), clearly distinguishing it from other osirApp* siblings like deploy, delete, or set-secret. It also explains the key side effect: the connection string becomes the app's DATABASE_URL secret.

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 makes its purpose and lifecycle context clear: provisioning a database whose credentials are injected at the next osirAppDeploy. It does not explicitly name alternatives or state when not to use this tool, but it provides enough context for an agent to choose it over related app-management tools.

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