chat_poll_messages

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

With no annotations provided, the description carries the full burden. It discloses the return format (structured JSON with messages and next_since) and the cursor-based statefulness of the polling behavior. However, it does not disclose whether this is a safe read operation, permission requirements, or any rate-limit/polling-frequency expectations. The read-only nature is implied by 'poll for messages' but not explicitly stated.

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?

Well-structured with a front-loaded purpose sentence, an Args section, Returns section, and a usage example. The KB reference adds navigational value. Slightly verbose but every section earns its place; the example is concise and illustrative.

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 polling tool with an output schema, this is fairly complete. It explains the incremental cursor pattern, session scoping, limit, and points to a KB doc. The only gaps are lack of behavioral disclosure around permissions and polling etiquette, which are minor for a read-only message poller.

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 0%, so the description fully compensates. It adds real meaning to all three params: 'since' is explained as an ISO-8601 timestamp with cursor fallback behavior, 'limit' as max messages, and 'session' as named session vs legacy default. This goes well beyond what the bare schema (with only defaults) provides.

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?

States a specific verb (Poll) and resource (new human messages from the UE editor chat widget), clearly distinguishing it from chat siblings like chat_send_response, chat_get_context, and chat_list_sessions. The resource and source are unambiguous.

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 description explains the polling pattern well: the 'since' cursor behavior and the previous-cursor fallback are described, along with session and limit parameters. However, it does not explicitly state when NOT to use it or name alternatives (e.g., chat_get_context for retrieving conversation history). The usage context is implied but not stated as exclusions.

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