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

Well beyond the annotations, it explains idempotency semantics (same key+payload returns the original orderRef; same key with different payload is a conflict naming differing fields), the 100-disc minimum enforced here, manual_exception for non-built-in sizes, and the human approval and payment boundaries. It stops short of stating auth requirements or rate limits, so it is not quite maximal.

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 purpose, then idempotency, then constraints, then routing and human-boundary notes, so the structure is well ordered. It is dense and a few clauses ('indistinguishable downstream', 'the lock-in write behind both recap exits') add flavor rather than instruction, keeping it just short of a 5.

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 15-parameter, 9-required mutation with no output schema, it covers return values (orderRef, quote, chosen exit, next step), the specific failure modes (recap mismatch, key reuse with different payload, contact email mismatch), and the human approval/payment boundaries. Nothing an agent needs in order to call it correctly is missing.

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 adds real meaning on top: quantity's 100-disc floor is enforced at this call, size values other than the two built-ins return manual_exception, recapRef inputs must match the recap, and idempotencyKey behavior is spelled out. It does not cover optional params like artworkRef, antiMetalCount, or linkDestination beyond the schema.

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 (set up an order) and pins down the mechanism ('an INVREQ record the hourly adoption resolves into the CRM'), which distinguishes it from sibling reads like get_order_status or get_quote. It also positions it in the flow relative to start_order_intent, get_recap, and request_invoice.

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 Routing section gives explicit ordering: start_order_intent is the earlier keyless contact capture, get_recap must run immediately before this call over the same inputs, and request_invoice follows. It also states exclusions indirectly by assigning contact capture and invoicing to other tools.

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