update_stack

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

Beyond the destructiveHint annotation, the description discloses specific behavioral impacts: containers are recreated with brief downtime, confirmation is required, and existing environment configuration is preserved automatically. These details help the agent anticipate side effects and guardrails.

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 two brief sentences that front-load the core purpose and include essential warnings. Every clause adds value—no filler or redundancy.

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 purpose, safety, confirmation, and behavior sufficiently for this simple tool. It does not mention return values or error cases, which is a minor gap given there is no output schema, but overall it is well-rounded for the tool's likely usage.

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?

With zero schema description coverage, the description compensates by clarifying that 'compose' is the YAML content and that 'confirm' must be true. 'stack_id' is not explicitly described but is obvious from the tool name and context. This adds meaning beyond the bare schema.

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 opens with 'Redeploy a stack with the given compose YAML', which clearly specifies the action (redeploy), resource (stack), and key input (compose YAML). This distinguishes it from sibling tools like restart_stack, which restarts without changing the compose configuration.

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 provides context that this is destructive, requires confirm=True, and preserves existing environment variables. It does not explicitly name alternatives for when a simple restart is sufficient, but the destructive warning and required confirmation outline appropriate usage conditions.

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