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 does disclose tenant inference, which is useful, but it does not explain whether invocation triggers side effects, whether async returns immediately, what stream output looks like, what callback_url does, or how failures manifest.

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 a single, front-loaded sentence with no filler. Every phrase contributes: the core action, the three call modes, and the tenant_slug behavior.

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?

This is a 10-parameter tool with no required fields, no output schema, no annotations, and only 50% schema documentation. The description does not resolve how to identify the workflow, which params are needed for a successful invocation, what the response contains, or how async/stream behave.

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 50%, and the description essentially repeats tenant_slug optionality already in the schema and lists invoke_mode enum values without adding meaning. It adds no guidance for env, input, version, callback_url, or the deprecated workflow id aliases.

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 'Invoke a workflow', a specific verb and resource that clearly distinguishes the tool from siblings like create_workflow, get_workflow, and publish_workflow. It also names the three invocation modes, so an agent immediately knows what the tool does and how it can be run.

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?

There is no guidance on when to choose sync, async, or stream invocation, nor when to use this tool instead of get_invocation, get_logs, or create_workflow. The description gives no working context, prerequisites, or exclusions.

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