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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the bar is lower. The description adds real behavioral context beyond them: it discloses the underlying model (conversion decays as response delay grows) and that the output is a per-month lost-deal/revenue estimate. It omits any statement of output units or sensitivity, which keeps it from a 5.

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 first sentence is front-loaded and efficient. The second sentence is a promotional link to an external site and contributes nothing to selection or invocation, which costs it a point despite the overall brevity.

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 stateless five-input calculator with fully documented parameters and a boolean-safe annotation set, this is close to sufficient. However, there is no output schema and the description doesn't say what the result contains (single lost-revenue figure, breakdown of lost deals vs. revenue, monthly vs. annual) or how the decay curve is specified, leaving the agent guessing at return shape.

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 every parameter has its own description (units, percentages), so the schema carries the semantic load. The description adds no parameter-level detail — no mention of what currentResponseMinutes vs targetResponseMinutes does to the model, or that conversionAtTargetPct is the anchor rate. 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?

The description states a specific verb and resource: estimate deals and revenue lost per month from slow lead response, with the modeling premise (conversion decays with delay). That is clearly distinct from siblings like form_field_friction_cost_calculator or inbound_call_center_routing_auditor. It stops short of naming an alternative tool, so it lands at 4.

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?

Usage is implied by the purpose ('slow lead response times' implies the user has current and target response times and wants a cost estimate), but there is no explicit when-to-use/when-not, no prerequisites, and no pointer to a sibling tool that handles an adjacent question. This is minimum-viable guidance.

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