process_sales_agent

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

The description enriches the annotation flags (readOnlyHint: false, idempotentHint: false) with concrete details: it 'ACTS on a real conversation,' can send messages or book meetings, 'CONSUMES AI CREDITS,' is 'not idempotent,' and requires an API key and confidence threshold. This far exceeds what annotations convey and prepares the agent for side effects.

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 at ~90 words and front-loads the primary action. It uses structured warnings with ALL CAPS ('CONSUMES AI CREDITS') and line breaks to emphasize risks. While clear, the ALL CAPS and em dashes make it slightly harder to parse quickly, though still efficient.

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 tool's high-stakes, side-effecting nature, the description covers all critical dimensions: real-world impact, cost, non-idempotency, authentication, and confidence threshold. It does not explicitly state a return value, but this is mitigated by directing users to get_sales_agent_actions for historical actions. Overall, very thorough for its complexity.

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?

The input schema already provides full 100% description coverage for the single conversationId parameter. The description adds contextual context ('over one conversation') but doesn't add new syntactic detail about the parameter itself. Baseline 3 is appropriate because the schema carries the load, and no clarification is needed.

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 starts with a clear, specific verb+resource: 'Run the sales-agent pipeline over one conversation: decide the next action and carry it out.' It goes on to list concrete side effects (reply to prospect, create deal, book meeting) and names a sibling tool for past actions, fully distinguishing itself.

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?

The description provides explicit when-to-use guidance: 'call it only when the user wants the agent to take its turn on that specific conversation.' It also names the alternative, get_sales_agent_actions, for retrieving what the agent has already done, and clarifies it is not a dry run.

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