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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuine behavioral value by exposing the cost formulas and the requirement that all tool fields be nested inside an 'inputs' object. It does not discuss return shape, but an output schema exists, so that omission is acceptable.

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 front-loaded with the purpose and formulas, which is the right ordering, and the formula sentences earn their place. However, the trailing sentences about 'units' (absent from the schema) and 'the REST calculator field' are opaque and consume space without resolving anything actionable. A tighter version would drop or clarify those references.

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 nested-object calculator with an output schema, the description covers the critical call-shape detail (all fields go inside 'inputs') and the math semantics. What holds it back is the misleading mention of 'units' and a vague prohibition about a 'REST calculator field' that cannot be resolved from the supplied schema, which could cause an agent to hesitate or guess.

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?

Although schema description coverage is 0%, the description compensates well: it maps the parameters into concrete math (per transaction = sale x (pct + extra_pct) + fixed; monthly = per transaction x count + monthly fee), which clarifies how 'fixed', 'monthly' and 'extra_pct' actually combine — meaning the bare schema does not convey. The nested-object requirement is also spelled out. It loses a point for referencing a 'units' field that does not exist in the inputSchema, which introduces ambiguity.

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 uses a specific verb ('Compare') and a specific resource ('monthly acceptance cost of payment methods'), and enumerates the input categories (card, crypto, ACH) plus the exact cost formulas. An agent can immediately tell what the tool computes. It does not, however, distinguish itself from sibling calculators such as buscalc_chain_invoice_quote or buscalc_chain_cost_basis, so it falls short of a 5.

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?

There is no guidance on when to choose this tool over alternatives, nor any stated preconditions beyond input-shape instructions. The imperative sentences ('Put tool fields inside inputs', 'Supply units or modelVersion only when listed in inputSchema') govern how to call the tool, not when to select it. Usage is only inferable from the stated purpose, and the absence of any sibling routing among a large catalog is a real gap.

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