Create service

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

Goes well past the annotations by disclosing non-idempotency in concrete terms ('calling this again creates another service, even with the same name'), the deferred-domain behavior, and an explicit anti-hallucination instruction about the null `domain` field. The 'later pushes or commits deploy again' note explains ongoing side effects that readOnlyHint/destructiveHint cannot convey.

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?

Front-loaded with the selection condition and every sentence carries operational weight, but the domain-null guidance is spread across three sentences ('that is expected', 'do not invent', 'tell the user...poll...') that restate the same instruction with some 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?

With no output schema, the description takes on the return-value burden and does it: it explains the `domain` field's null-on-creation state, why it is null, and how to obtain the real value. For a mutation tool with nested envVars and a deferred build, nothing essential is missing.

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?

At 57% schema coverage the description should compensate, and it does for repoUrl (the omit/provide fork and the deploy-on-push behavior are genuinely beyond the schema). But name, region, envVars, and containerPort get no treatment in the description, leaving a meaningful share of parameters carried by the schema 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 and immediately splits the two operating modes (empty service vs. repo deploy) with concrete repo formats. It also explicitly carves out the boundary against the update path by saying a repeat call creates another service, so an agent can distinguish this from service_set or service_rename without opening any schema.

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 an explicit trigger ('use this when the user wants to create'), an explicit branch condition (omit repoUrl vs. provide repoUrl, with the consequence of each), and names the follow-up tools to use instead of guessing (service_show, deploy_events). The 'does not update an existing one' clause routes the update case away from this tool.

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