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

The description discloses meaningful side effects beyond the annotation flags: a draft profile is created and gated behind human approval, credits are charged, and credits are refunded on failure. This gives the agent an accurate cost and safety model.

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 tight sentences, each carrying distinct information: what the tool does, its prerequisite, and the draft/credit outcome. No filler or repetition.

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?

It covers prerequisites, the human-approval safety workflow, and cost/refund behavior well. With no output schema, it could say a bit more about what the call returns or how to track completion, but the saved-draft framing gives enough orientation for most agents.

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 baseline is 3. The description only indirectly touches parameters by noting the 50-message prerequisite; it does not add parameter-level syntax, defaults, or format details beyond what the schema already states.

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 opens with a specific action and resource: 'Run voice extraction for a LinkedIn account from its stored message history.' It also clarifies that the output is a draft profile requiring human approval, which separates it from read/update voice tools such as get_conversation_voice and update_conversation_voice.

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?

It gives clear situational context: the account needs at least 50 usable human-written messages and backfill runs at connection. It does not explicitly name alternatives or say when not to use it, so it falls short of a 5.

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