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

Annotations already flag destructive and non-idempotent behavior, but the description adds value beyond them: the concrete side effects (replying to the prospect, creating a deal, booking a meeting), the fact there is no dry run or preview, that it consumes AI credits, requires an API key, and that the confidence threshold gates action. This is a rich behavioral disclosure that goes well past what the structured fields convey.

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-loads the core purpose, then layers constraints, alternates, and warnings in short, scannable sentences. The emphasis on the credit and non-idempotency warnings is deliberate and earns its space given the destructive nature of the call.

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 single-parameter tool with no output schema, the description covers purpose, side effects, safety warnings, prerequisites, and the sibling alternative to use for read-back. Nothing an agent needs to invoke it safely is missing.

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 description coverage is 100% and the single parameter conversationId is fully documented in the schema, so the description adds no syntax or format detail. The phrase 'over one conversation' loosely contextualizes the parameter but is not meaningfully additive, so the 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 verb and resource ('run the sales-agent pipeline over one conversation') and immediately explains the decision-plus-action nature ('decide the next action and carry it out'). It is clearly distinguishable from siblings like get_sales_agent_actions, which it explicitly contrasts.

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 an explicit when-to-use condition ('call it only when the user wants the agent to take its turn on that specific conversation') and names the alternative tool for the read-only case ('For what it has already done, use get_sales_agent_actions'). Both the trigger and the exclusion are spelled out.

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