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

Annotations already declare read-only, idempotent, closed-world behavior, yet the description still adds real context: refusal on incomplete items, side effect of defaults being surfaced in defaults_applied, volume discounts aggregated across all items, prices excluding shipping/sales tax, and that nothing is ordered or saved. It also tells the agent to show the returned picture to the user, which is behavioral guidance not present in 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?

Front-loaded with what the tool returns and does, then the required-field rule, then defaults and pricing caveats. Dense but nearly every sentence carries information; a few clauses (e.g. restating the discount rule twice) could be trimmed without loss.

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 complex, nested-array pricing tool with an output schema, the description covers what is returned at a useful level (picture, configurator_url, defaults_applied), the failure mode, the defaulting behavior, and the pricing boundaries (discount aggregation, shipping, tax). An agent has everything needed to call it correctly and to relay results to the 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 baseline is 3; the description earns above that by explaining the interaction protocol (never guess, ask end A and end B separately, ask about JST GH), that a complete design code/URL satisfies all requirements, and that defaults are reported back in defaults_applied rather than silently applied.

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 ('Price one or more custom wire harness designs exactly as acornharness.com checkout will') and makes clear this is a simulation of checkout pricing, not an order. That distinguishes it from create_order and list_options without naming them.

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 strong operational guidance: items missing required fields are refused with questions, 'ask the user, don't guess', and ask end A and end B separately. It implies this is the pre-order quoting step ('Nothing is ordered or saved') but never explicitly names create_order as the follow-up or states exclusion conditions in tool terms.

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