Put a live call on hold

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

Annotations already declare destructive/openWorld/idempotent hints, so the bar is lower, but the description still adds real behavioral context: the hold works by transferring the leg to a hosted flow, music loops until resume, and it only works in HTTP mode with VOBIZ_PUBLIC_URL. It does not detail the effect on the live call state during the hold, a minor 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?

Four short, front-loaded sentences with no filler; the mechanism, the resume path, the mode constraint, and the confirm requirement each carry information. Slightly choppy phrasing ('and the XML URL that should take over') but nothing wasteful.

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 mutation tool with no output schema but full annotation coverage, the description supplies the mechanism, resumption path, mode constraint, and confirmation requirement an agent needs to invoke it correctly. Only the state effect on the call during hold is unaddressed.

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 75%, so the schema already documents legs, confirm, and music_url well. The description reinforces the confirm requirement and that music is optional (silence if omitted), but adds little syntax or meaning beyond what the schema fields already say. Baseline 3 is appropriate.

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 ('Puts a leg on hold') and explains the mechanism (transferring to a hosted flow playing hold music or silence on loop). It also names the counterpart action, unhold_call, so the agent can distinguish this from its resume sibling without opening schemas.

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?

Explicitly names unhold_call as the way to resume, and states two preconditions: 'HTTP mode with VOBIZ_PUBLIC_URL only' and 'Requires confirm: true.' This gives clear context for when the tool is valid, though it stops short of stating when-not-to-use or distinguishing from play_audio/stop_audio alternatives.

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