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

With no annotations, the description carries the full burden of behavioral disclosure. It explains that the first deploy creates the tool and later deploys replace the running container, requires a Dockerfile listening on $PORT, and mentions the STALE_BASE refusal for stale base values. It does not mention permissions or atomicity, but the central mutation behavior is explicit.

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 dense sentences with no filler. The action and outcome are front-loaded, followed by the critical file contract, then the versioning safeguard. 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?

Given there is no output schema and no annotations, the description covers the essential lifecycle, file requirements, and the stale-base failure mode. It does not state what a successful response contains or enumerate other validation failures, but an agent has enough to invoke the tool correctly and interpret its key risk.

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 schema covers all parameters, so the baseline is 3 distributed. The description adds valuable semantics beyond the schema: files must include a top-level Dockerfile listening on $PORT, and base should be the release number from pull to prevent silent overwrites. These constraints are not fully expressed in the parameter descriptions alone.

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: deploy a folder as a tool and make it live at a URL. It clearly distinguishes creation on first deploy from replacement on subsequent deploys, differentiating it from sibling operations like get_tool, list_tools, rollback, or restart.

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?

Gives clear context: use this tool to make a folder live as a tool. It adds a specific when-condition around the base parameter, warning to pass the pulled release number to avoid silently overwriting a concurrent deploy, but it does not explicitly exclude alternatives like rollback or restart.

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