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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the safety bar is lower. The description does add real value by describing the return shape (sender handles, timestamps, direction, delivery confirmation). However, it is silent on the mutation surface: delete_workflow is an irreversible operation that the description never discloses, and nothing is said about permission/auth requirements for dispatching replies on each network.

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 sentences, well front-loaded: scope first, operations second, return value last. The platform roll-call in sentence one is somewhat expendable given the `platform` enum already lists them, but overall there is little waste. The brevity is not padding — the problem is coverage, not verbosity.

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?

With 12 parameters, nested node/edge graph objects, no output schema, and a destructive delete_workflow action, the description covers well under half the capability surface. An agent could invoke this tool believing it only lists and replies to DMs, and be blindsided by workflow-graph semantics (nodes, edges, triggerPayload, cooldownHours) that appear nowhere in the prose.

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 100%, so the baseline is 3. The description does not add anything beyond the schema for individual parameters — it does not explain the threadId/action coupling, profileId scoping, unreadOnly semantics, or cooldownHours behavior. It also restates only 4 of the 11 `action` values, leaving the workflow-related enum members undiscussed in prose.

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?

Names a specific resource (the unified cross-network inbox) and enumerates the concrete inbox operations it performs, with the six platforms spelled out. It is clear what the inbox half of the tool does, but it never mentions the workflow-automation half (create/get/activate/pause/trigger/delete_workflow) that dominates the action enum, so an agent looking for workflow management would not recognize this tool. No sibling tool is named as an alternative or contrast.

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?

Usage is only implied by the parenthetical action list — the reader must infer that you call list_threads first, then read_thread/reply/mark_read. There are no explicit when-to-use or when-not-to-use conditions, and no routing against siblings such as telecom_messaging or comments_moderate, which plausibly overlap on outbound messaging.

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