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

With no annotations provided, the description carries the full behavioral burden. It explicitly states 'Delete' (a destructive action) and mentions authentication, which is helpful. However, it does not disclose that deletion is likely permanent, does not mention side effects on messages or related data, and does not state whether the operation can be undone. Basic transparency is present, but more is expected for a destructive 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?

The description is a single, concise sentence that leads with the action and includes key parameters and authentication. There is no unnecessary filler, and it is appropriately front-loaded. It could slightly expand on usage guidance without becoming verbose, so it is not a perfect 5.

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 simple delete operation, the description covers the core action, accepted parameters, and auth requirement. However, it lacks important context such as the irreversibility of deletion, the need to provide exactly one of the two identifiers, and any prerequisite steps (e.g., that room_name comes from list_conversations, although the schema implies this). The absence of annotation makes this more critical, so a 3 reflects the gap.

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?

The schema description coverage is 100%, and the schema already explains both parameters: room_name is 'Room name from list_conversations' and talent_slug is 'Talent slug (from search_talent results) — resolves to room name automatically.' The tool description merely repeats 'Accepts room_name or talent_slug' without adding new semantic meaning. Baseline is 3 due to high schema coverage, and the description does not elevate it.

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 the action clearly: 'Delete a conversation.' It names the resource and the verb, and it mentions the two accepted identifiers. While it does not explicitly differentiate from siblings, the tool name itself and the action make it distinct from nearby tools like get_conversation or start_conversation, so it is sufficiently clear.

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 provides one usage constraint ('Requires employer authentication') but gives no guidance on when to use this tool versus alternatives, such as when to delete versus archive, or how to obtain the required identifiers. It does not mention that a conversation must first be listed (e.g., via list_conversations) or that only one of the two parameters should be provided. This leaves the agent to infer usage conditions.

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