device_ble_state

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, so the safety profile is covered and the trailing 'Read-only' is redundant. The description does add genuine context about what the returned signal means (a failed connectionCount implies every reconnect, including enterLoader during upgrades and BLE drops, will fail), which is useful behavioral insight. It does not describe freshness/polling behavior or the shape of the response.

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?

Two tight sentences, front-loaded with what is reported before the failure-mode caveat. Only waste is the closing 'Read-only', which merely repeats readOnlyHint=true from the annotations.

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 no output schema, the description must carry the return-value burden, and it names the key fields plus the semantics of the critical connectionCountOk flag and its remediation. It does not enumerate the full response shape or whether results cover all devices or one, which is a minor gap given the 'per device' phrasing and empty input schema.

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?

Zero parameters, so there is no parameter meaning to convey and baseline 4 applies. The description wisely spends its space on interpreting returned values instead.

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 ('Live BLE link state per device') and enumerates the exact facets it reports: GATT connected, store vs. manager status, pool membership, loader mode, connectionCount. It does not explicitly contrast itself with the adjacent device_status / device_pool_state tools, so an agent must infer the boundary, but the reported field list makes the tool's niche 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?

Gives a concrete usage signal: when connectionCountOk=false, reconnect attempts will fail with RECONNECTION_INTERRUPTED, and the fix is device_ble_heal. That routes the agent to the correct sibling for remediation. It stops short of saying when to prefer this over device_status or device_pool_state, so no explicit exclusions or alternatives beyond the heal path.

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