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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description builds on this by adding genuinely new behavioral context: the computation is deterministic, nothing is ordered, and the result is only an estimate pending written confirmation from Zicron. Since there is no output schema, the description of the return breakdown (base price, pages over included amount, first-case discount, total, turnaround) must be carried by the description, and it is. No contradiction with annotations.

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 sentences, no filler. The primary action and return value are front-loaded in sentence one, the usage trigger sits in sentence two, and the estimate caveat closes with essential expectation-setting. Every sentence earns its place.

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 simple 2-parameter calculator with no output schema, the description covers everything an agent needs: what it computes, what it returns, when to invoke it, and the critical caveat that the price is an estimate pending written confirmation. The safety profile is covered by annotations, and the read-only/estimate framing fully prepares the agent to communicate the result correctly to a user.

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%, so the schema fully documents both pages and first_case. The description's references to 'approximate page count' and 'first-case discount' reinforce but do not extend the schema content. Baseline 3 applies because the schema does the heavy lifting and the description adds no new parameter-level meaning.

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 — 'Computes the price of a Zicron medical chronology from the approximate page count' — and enumerates the exact output components (base price, pages over included amount, first-case discount, total, turnaround). The explicit 'Use this when a user asks what a chronology for N pages would cost' differentiates it from siblings like request_chronology and get_offer without needing to open their schemas.

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 gives a clear, direct trigger condition: 'Use this when a user asks what a chronology for N pages would cost.' It also implies a non-ordering boundary ('nothing is ordered', 'Zicron confirms... before any work starts') that separates it from requesting work. However, it never names alternatives explicitly (e.g., pointing to request_chronology when the user wants to place an order), so it falls just short of the 5 bar.

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