Create service

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

Despite annotations already marking idempotentHint=false, the description adds concrete non-idempotency detail: calling again creates another service even with the same name. It discloses the async domain-assignment behavior (domain null until build/boot, expected not an error) and an error-prevention rule (do not invent/guess a hostname), all of which go well beyond the annotation flags. No contradiction with annotations.

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?

A single ~150-word paragraph with no filler; every sentence delivers load-bearing behavioral or usage information. It is front-loaded with the use case and follows a logical order (when → how → caveats → follow-up). Slightly long and wall-of-text formatted, but justified by the density of critical guidance.

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 state-changing 7-param create operation with no output schema, the description covers the high-risk failure modes: non-idempotency, async domain assignment (naming the response's `domain` field explicitly), and the correct follow-up workflow. Minor gaps remain — it never summarizes the broader response shape or the semantics of envVars/containerPort — but the critical decision and error paths are fully covered.

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 57%, so the description carries some burden for undocumented params (project, envVars, containerPort). It adds real strategic meaning for repoUrl — the two-mode decision (empty vs immediate deploy) that determines whether to populate repoUrl and skipInitialDeploy — beyond the schema's one-line property description. It does not, however, compensate for the three schema-undocumented parameters.

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 names a specific verb-resource pair — create a new Lizard service — and enumerates two concrete modes: empty service versus deploy-from-GitHub-repo. It further disambiguates from siblings by stating it never updates an existing service, which separates it from service_set/service_rename. An agent can tell exactly what this tool does and roughly what it is not.

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?

Opens with an explicit 'Use this when the user wants to...' scoping rule and gives a decision rule between the two modes (omit repoUrl vs provide it). It states an exclusion — 'it does not update an existing one' — and names concrete alternative tools (service_show, deploy_events) for the follow-up polling flow. Nothing is left to inference.

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