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

Annotations only declare readOnly/idempotent/non-destructive/openWorld; the description goes well beyond that by explaining why fields are null (canSend/canReceive null because operational availability is unknown), why SMS is not_checked, what shared_setup_state actually represents, and which permissions gate specific sub-results (billing:read for registration detail, agents:read for private_test_readiness). It also corrects likely misreadings, e.g. that a connected mailbox does not prove campaign approval or delivery and that private testing does not establish outbound call permission. This is exactly the beyond-annotation behavioral context that changes how an agent reports results; 'Read-only; changes nothing' merely restates readOnlyHint.

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 lead sentence is front-loaded and the content is substantive rather than filler, but the body is a dense wall of comma-spliced clauses ('...not_checked with reconnect scope guidance. Private testing does not establish...') with no list or grouping by channel. Channel-by-channel facts would be far more scannable as structured bullets, and the final 'changes nothing' clause duplicates the readOnlyHint annotation.

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 read-only status tool with a rich output schema, the description supplies the missing semantic layer: null-versus-not_checked meaning, permission-gated fields, and explicit caveats about what the fields do not prove. Annotations cover the safety profile and the output schema covers the return shape, so the remaining gap is only the undocumented business_id input. Complete enough that an agent could call and interpret it confidently.

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?

There is a single required parameter, business_id, with 0% schema description coverage, and the description never mentions it at all. The parameter name is largely self-explanatory, so the cost of the omission is modest, but the description does nothing to compensate for the empty schema and gives no guidance on format, source, or scope of the identifier. Baseline is pulled down from the 0-param case by the explicit coverage gap.

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 opening sentence 'Read customer channel setup' gives a specific verb and resource, and the following sentences enumerate exactly what is covered per channel (phone number state, SMS state, private_test_readiness, managedEmail campaign readiness). This lets an agent infer it is the aggregate per-business channel readiness read. It stops short of naming which sibling to use instead (e.g., get_phone_system_status, get_email_campaign) or stating that it is the multi-channel rollup versus those single-channel tools.

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: the agent can tell to call this when it needs a channel-by-channel setup summary, and the billing:read/agents:read notes hint at required scopes. There is no explicit 'use this instead of X when Y', no statement of preconditions for the calling agent, and no guidance on when a narrower sibling status tool is preferable. The scope statements do effectively tell the agent what it will NOT learn (outbound permission, customer coverage), which is partial exclusion guidance.

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