Run local conversation tests

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

With no annotations, the description carries the full behavioral disclosure burden. It states that tests run only against the published agent, that every result reports the observed topic, tool and citations even when not asserted, and that it reports pass/fail. It does not explicitly state whether running changes anything or its effect against the agent, but its non-destructive nature is strongly implied except for writeExample.

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?

Four sentences carry distinct loads: the invocation target, the assertion semantics, the reporting behavior, and a positioning/cli tip. It is dense and useful, with no empty filler, though the writeExample tip slightly repeats what the schema already says.

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 15 parameter tool with no output schema, the description does well: it explains the YAML format, the assertion surface, the through-cs_chat execution path, and the report content (pass/fail, plus always-present observed topic, tool, citations). It does not detail the full output structure or the remaining undocumented params, but an agent can meaningfully formulate and parse the results.

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 60%, so the description must compensate. It adds real meaning to the most critical and least-constrained parameter, expect, by enumerating its supported assertion forms (contains, containsAny, notContains, regex, minLength, noSignIn, usedTool, notUsedTool, usedTopic, notUsedTopic, citedKnowledge). It also describes the YAML test file shape. Parameters like file, stopOnFail, dataverseUrl, and directLineSecret remain without explanation.

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 states a specific verb+resource: "Run a YAML test file" against "the published agent through cs_chat" and report pass/fail. It also explains the assertion scope (wording plus tool/topic/citation checks), which separates it from a plain chat or evaluation tool. It does not explicitly name sibling tools like cs_run_evaluation, so the distinction is clear but implicit.

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?

The phrase "The CLI-native complement to portal evaluations" locates the tool relative to portal-style evaluation UX, and "through cs_chat" suggests it parallels the chat tool. However, it does not explicitly name alternative siblings (cs_run_evaluation, cs_create_test_set_csv, cs_create_test_set) or specify a when-not-to-rule, so guidance is inferred rather than stated.

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