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

With no annotations, the description carries the transparency burden and does well: it discloses the ≤3 card limit, mock latency under 400ms, compat-stub behavior, idle cost, no-live-PSTN constraint, and lab-only TEMSOR_RTP_LAB behavior. It loses a point because terms like 'whisper cards' and 'in-call index' are not explained, and the lab_latency_ms field's role remains ambiguous.

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 description is compact and front-loads the core purpose, but it repeats 'Idle $0' and mentions lab_latency_ms twice. The first line mixes shorthand fragments without a clear logical order, making the text feel denser than necessary.

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?

Given the absence of an output schema, the description provides a reasonable high-level return contract (open promises/facts, max 3 whisper cards) plus important environment and latency constraints. It does not define exact card fields, auth, or error behavior, but it covers far more than the minimum for a two-parameter tool.

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%, so the schema already documents call_id and partial_text; the description adds useful nuance about preferring the in-call partial index. However, the mention of 'optional lab_latency_ms when TEMSOR_RTP_LAB=1' is ambiguous because that field is not present in the input schema.

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 description clearly states that the tool 'Returns open promises and facts as whisper cards for agent handoff' and gives the concrete endpoint and payload shape. It is specific and useful, but it does not explicitly differentiate itself from related PBX siblings such as pbx_whisper_status or pbx_promises, so it falls short of a 5.

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 context is implied: it is for live-agent handoff, prefers an in-call partial index, and the 'No Telnyx/DID/live PSTN' caveat signals it is not for live telephony. However, there is no explicit 'use this instead of X when...' guidance, so the agent must infer when this tool should be selected over its siblings.

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