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

Annotations already disclose non-read-only, non-destructive, non-idempotent behavior, and the description adds genuinely new context: a reference number is issued and shown on screen, a human reviews submitted details and sources permit-holding haulers, the response arrives by email with a proposed calendar, invoicing model and firm price, and contact details are purged after 180 days. This is substantive disclosure beyond the annotation flags. The one gap is that it never warns that resubmitting (idempotentHint=false) will create a separate reference.

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 core action is front-loaded, but the opening is repetitive, stating twice that a reference number is issued and kept. The sentence 'Your board is recorded as a request and given a reference number, shown on screen when you send it' is garbled and adds no information. Several sentences could be condensed without losing content.

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 an eight-parameter, nested-object tool with no output schema and zero schema description coverage, the description explains the outcome flow well but leaves the input contract almost entirely unexplained. An agent still cannot tell what belongs in 'specifications' versus 'quantity', what 'action' should be set to, or what format 'need' takes. That is a substantial completeness gap given the tool's complexity.

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 0% across eight parameters with nested objects, so the description must carry the load and it only partly does. It gives domain meaning to the details being submitted (locations, trap sizes, frequencies, pump-outs, haulers, service windows) and indirectly references contact.email, timing and budget via the promised reply. It never maps to parameter names such as 'need', 'action', 'quantity' or 'specifications', nor explains the action enum, leaving the agent to guess which field carries what.

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 opens with a clear verb and resource and names the recipient, so the agent knows this submits a requirement to Quarterline for sourcing. It is distinguishable from the only sibling, describe_business, which describes rather than submits. The purpose is clear even though the second sentence ('Your board is recorded as a request...') muddies the subject.

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?

Usage is implied through the non-committal framing ('Nothing is scheduled, ordered or committed until you agree terms'), which tells an agent this is a safe pre-sales inquiry rather than a booking. However, there is no explicit when-to-use or when-not-to-use statement and no named alternative, so the agent has to infer call conditions.

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