run_flow

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

The description discloses the async contract precisely: wait up to wait_seconds, return immediately if 0, return a pollable job_id if not finished, and include resource usage, timing, and errors on completion. It also notes the stage-flow dependency and that compile is the full path. This goes well beyond the sparse annotations (readOnlyHint/destructiveHint false).

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 short paragraphs front-load the core action, then clarify flow semantics and wait/poll behavior. Every sentence carries distinct information with no filler or repetition.

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 long-running async operation, the description covers the key return behavior (job_id vs final result), the flow enum semantics, and result contents. The main gap is the unmentioned timeout_minutes parameter and exact failure/timeout behavior, but the overall picture is sufficient for an agent to invoke it and know how to monitor the job.

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?

Flow and wait_seconds are explained in meaningful operational terms, and project is obvious as a required identifier. However, schema description coverage is 0% and timeout_minutes is never discussed, so the description only partially compensates for the missing parameter documentation.

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?

Description opens with an explicit verb and resource: 'Run the Efinity flow with efx_run.' It then defines what 'compile' means and the stage alternatives, distinguishing this from sibling run/build tools. The purpose is unmistakable and includes the domain-specific flow context.

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?

It tells the agent when to expect a full build vs a single stage, warns that stage runs require earlier stages to be current, and explains when a job_id is returned for polling with get_job_status. It stops short of explicitly listing when not to use run_flow relative to sibling tools like run_sta_tcl or program_device, so it is clear context without full exclusion guidance.

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