conduyt_ai_call_disposition

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

With no annotations, the description carries the full burden and does so well: the HTTP 202/pending:true polling contract, the fact that a pending answer costs nothing, that no disposition is applied, the recorded-vs-unrecorded fallback behavior, and the dialer:view permission requirement. These are exactly the behavioral traits an agent needs and none are in the schema.

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?

Front-loaded with the core purpose, then the two regimes, then the safety/permission facts. It is dense with parenthetical asides and long clauses but essentially every sentence carries a distinct fact; only minor tightening would help.

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?

Despite no output schema and no annotations, the description enumerates the return payload (summary, disposition with confidence, deal stage move, follow-up), covers the pending/202 state and its polling remedy, and states the permission prerequisite. An agent has everything needed to call and interpret it correctly.

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 single callId parameter is already documented as the call UUID. The description references 'the call's details' but adds no syntax, format, or validation nuance beyond what the schema provides, so 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 resource (AI-suggested call disposition) and describes exactly what the answer is in two distinct regimes: recorded calls yield the post-call copilot's grounded insight, unrecorded calls fall back to a metadata classifier. An agent can tell this differs from raw insight retrieval, though it never names the close sibling conduyt_get_post_call_insight explicitly.

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 conditions: for recorded calls the insight exists once the transcription worker has built it (poll again when 202/pending:true), otherwise a classifier proposes from call details. It states polling is cost-free when pending and that nothing is applied. It stops short of naming an alternative tool to use instead, so it is not a full when/when-not routing guide.

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