Preview what a hangup would drop

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'without touching them' and the read-only-mode note, then adds genuinely new behavioral detail: it reports the matching channel plus the leg it is bridged to. It does not describe behavior when the UUID matches nothing or how ambiguous partial matches are resolved, which is the remaining gap.

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 short sentences, zero waste. The non-destructive nature and blast-radius framing are front-loaded, and the availability note is placed last where it belongs as a caveat.

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 one-parameter read-only preview with no output schema, the description covers purpose, safety, return content ('the matching channel plus the leg it is bridged to'), and availability. The one missing piece is what the caller sees when nothing matches or when the partial UUID is ambiguous, which matters for a preview tool whose whole job is reporting.

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 100% and the schema already documents the single uuid parameter, including partial-match support ('or part of one'). The description adds only that it is the 'same UUID argument as freeswitch_hangup', which is a useful consistency cue but not new semantics. Baseline 3 applies.

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 and resource ('Show which live call legs a hangup would affect') and immediately distinguishes itself from the mutating sibling by noting it does so 'without touching them' and takes 'the same UUID argument as freeswitch_hangup'. An agent can tell it apart from freeswitch_hangup without opening either schema.

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 clear context for when to reach for it: 'so you can see the blast radius first', i.e. before calling freeswitch_hangup, plus an availability note ('Always available, including in read-only mode') that tells an agent it can call this even under restrictive conditions. It stops short of explicitly naming when not to use it or naming the asterisk_hangup_preview sibling as the alternative for the other stack.

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