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

Annotations already declare destructiveHint and idempotentHint, but the description goes beyond them by specifying exactly what is destroyed (the chat history) and what survives (generated media stays in the project), plus the timing precondition. This is real behavioral context the agent could not infer from structured fields.

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 compact clauses front-load the action, destruction semantics, and precondition, ending with the endpoint. Every fragment carries information; nothing is redundant.

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 single-parameter destructive tool with annotations covering the safety profile and no output schema, the description supplies everything needed: what is deleted, what persists, and the precondition. No meaningful gap remains.

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?

Only one parameter (chatId) with 100% schema description coverage, so the schema baseline is 3. The REST path DELETE /agent/chats/{chatId} loosely corroborates chatId usage but adds no syntax, format, or ID-source detail beyond the schema.

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 (Delete) and resource (agent chat), and the parenthetical clarifies it also applies to the Flow web app. It is trivially distinguishable from siblings like flow_agent_chat, flow_agent_get_chat, or flow_agent_list_chats.

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?

Provides a clear when-not condition ('Not while a turn runs'), which prevents a common failure mode. However, it names no alternative tool or fallback for a chat that cannot be deleted, so it stops short of full alternative routing.

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