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

Annotations already declare the safe read-only, idempotent, closed-world profile, so the safety bar is met structurally. The description still adds useful behavioral context beyond the schema: it enumerates the possible states a flow can be in and clarifies the return volume ('Every flow is returned, so the number of rows is the number of flows'), which matters since no output schema exists.

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?

Front-loaded with the core action and ends with the return-size guarantee. Mostly earns its place, though the 'administrator manages them at Settings -> WhatsApp Flows' sentence is UI guidance of marginal value to an agent and the status enumeration duplicates the schema enum.

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 an optional-filter, read-only list tool with no output schema, the description covers the key gaps: what a flow is, how to filter, the prerequisite tool, and the fact that results are unpaginated/complete. Nothing essential is missing; ordering and default sort are the only unstated details.

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 only 33%: fields has a description, while status and inbox_id do not. The description compensates for inbox_id by tying it to list_inboxes, but adds nothing for fields and merely echoes the status enum values already in the schema. Partial compensation, so a baseline-plus 3.

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+resource ('List the WhatsApp Flows of this account') and goes further to define what a flow is (Meta's native in-chat forms) and its ownership (each owned by a WhatsApp inbox). An agent can distinguish this from get_whatsapp_flow, list_whatsapp_flow_sessions, and the create/delete/publish flow siblings.

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?

Gives explicit filtering options ('Filter by inbox_id ... or by status') and even sequences a prerequisite ('call list_inboxes first'). It does not mention when to use get_whatsapp_flow for a single flow, so routing is clear but not exhaustive.

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