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

Annotations already flag destructive, non-idempotent, open-world, but the description adds material context beyond them: it creates a customer record AND a quote at Detritus, triggers an outbound text and/or email to the customer, and warns that a repeat call for the same job duplicates the request. It also states the return value (serviceRequestId).

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?

Sentences are front-loaded and information-dense, with the core action first and side effects and retry warning after. The 'Requires the customer's first name, last name, email, phone, full delivery address, delivery date, and selected products' sentence partially duplicates the schema's required array, which is the only real slack.

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, destructive, open-world tool with an output schema and full annotations, the description covers side effects, duplicate risk, and the returned ID. The one gap is that it never mentions needing get_service_availability first to resolve product and dumpster IDs, leaving that to the schema's field descriptions.

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 every parameter including the nested customerConfirmed const and the request fields is already documented; the description only restates the required field list. It adds a little sequencing meaning around customerConfirmed but nothing about formats or the enum choices 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?

The description names a specific verb and resource ('Submit one quote request to Detritus for dumpster, portable sanitation, and/or other jobsite services') and states the cardinality rule that all items for a job go in one request. It implicitly distinguishes itself from read-side siblings like get_quote by describing creation of a customer record and quote, though it never names those siblings explicitly.

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?

It gives clear invocation context ('All items for one job go in a single request'), the confirmation prerequisite ('customerConfirmed: true after the customer has reviewed those details'), and a strong retry exclusion ('Not safe to retry'). What it lacks is an explicit pointer to get_service_availability as the prerequisite for product/dumpster IDs, which only the schema supplies.

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