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

Annotations cover idempotency and non-destructiveness, but the description adds valuable behavioral context: enabling makes the agent respond autonomously, confidence threshold gates actions, reply limits cap sending, and changes take effect immediately. This goes beyond the structured hints without contradicting them.

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 well-structured with a clear first sentence listing the action, followed by a focused paragraph explaining live implications and a short note on idempotency and auth. It is slightly verbose in the middle but each sentence earns its place by contributing critical context.

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 6 optional parameters, no output schema, and the tool's live-impact nature, the description covers the essential aspects: the live behavior, partial update semantics, need to read current config, and API key requirement. It lacks explicit return/error behavior, but the tool is a straightforward update and the description is largely adequate.

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 enriches several parameters: explains the impact of 'enabled' (starts responding), the meaning of 'confidence_threshold' (how sure before acting), and 'max_replies_per_day' (caps sending). While not all parameters get extra context (e.g., cal_link, offer_price), the description adds meaning to the most consequential ones.

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 the tool changes the AI sales agent's settings, listing specific fields (enable/disable, booking link, offer price, reply limits, confidence threshold). It distinguishes from sibling get_sales_agent_config by the action verb and scope, and from process_sales_agent by focusing on configuration rather than actions.

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 usage context: it advises reading the current config first, notes that only passed fields change, warns that enabling has immediate live effects, and indicates the tool is safe to repeat. It does not explicitly state when not to use it or name alternatives, but the guidance is sufficient for most scenarios.

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