Run flows

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: per-flow results with failing checks plus request/response or query evidence, and that it writes Markdown, JSON and JUnit report files as a side effect. What it omits is significant for a potentially mutating tool—no statement about required credentials/environment setup, whether flows can alter the target environment's data, or whether report writing is skipped when write_report is 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?

Two tightly packed sentences with no filler; the scope default is front-loaded right after the verb and the return/report payload follows. Every clause carries distinct information.

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 zero-annotation, no-output-schema tool with four undocumented parameters, the description supplies the result shape and the report side effect, which is genuinely useful. It remains incomplete on preconditions (auth, environment existence), mutation risk to the target environment, and tag filtering semantics—all things an agent would need before invoking it.

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 description coverage is 0% across four parameters, so the description must compensate. It partially explains paths (default tests/api/), environment (target of the run) and implicitly write_report (via the report formats listed), but tags is never mentioned and no parameter takes a format, syntax, or precedence rule, leaving the agent to guess at tag matching and null-vs-empty behavior.

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?

Uses a specific verb+resource ("Run flows") and names the default target scope ("everything in tests/api/") plus the environment dimension, which separates it from authoring siblings like draft_flow and write_flow. It stops short of explicitly contrasting itself with those siblings, so an agent must infer execution-vs-authoring.

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?

Implies usage context by saying flows run "against an environment" and that paths default to tests/api/, so an agent can infer this is the execution step. However, it gives no explicit when-to-use vs when-not guidance and never points at alternatives such as draft_flow for authoring or call_api for one-off calls.

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