Chat with the published agent

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

With no annotations, the description must carry the load; it does disclose response details (replies, raw activities, sign-in URL) and the continuation mechanism. However, it does not mention long-running behavior, the background flag, authentication requirements, or failure modes, which are significant for this tool.

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 sentences: the first defines the action and result, the second gives continuation guidance, and the third explains a special response. Every sentence earns its place and the core purpose is front-loaded.

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?

Given the rich input schema, the description covers the essential invocation flow and return behavior. It lacks explicit notes on long-running options and auth, but those are partially available in the parameter schemas; the absence of an output schema is partly mitigated by describing replies, raw activities, and signInUrl.

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 71%, so the structured schema explains most parameters. The description adds value by clarifying the main parameter, utterance, as a single utterance, and by explaining conversationId's role in continuing the conversation; it does not address the few undocumented parameters like schemaName or directLineSecret.

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 uses a specific verb and resource: 'Send one utterance to the published agent' and clearly states the output: 'replies (and raw activities)'. This is distinct from the many sibling tools, such as cs_review_agent or cs_get_org_agent, which are not conversation tools.

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 provides clear operational context: start with an utterance, continue with conversationId, and handle a sign-in card via signInUrl. It does not explicitly name alternatives or exclusions, so it stops short of full when-to-use/not-to-use guidance.

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