draft_quote

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

With no annotations, the description carries the behavioral burden well: it discloses auto-confirmation of exact matches, candidate presentation for non-exact requirements, and the important side effect that nothing is saved on the website. It also specifies units for sizes and bandwidth. It does not mention authentication or error behavior, but the key behavioral traits for this tool are covered.

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 compact and front-loads the core action before defining the requirements structure. Every sentence carries useful information about fields, matching behavior, or units. The inline JSON-like requirement format is dense but necessary, though it could be slightly easier to scan if structured more formally.

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 tool with an output schema, no annotations, and a required nested requirements array, the description covers the important operational context: requirement fields, automatic confirmation, user review flow, non-persistence, and units. It is nearly complete, with the only notable omission being the meaning or format of the customer parameter.

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%, so the description must compensate, and it largely does: it defines the requirement object fields, including id, service, region, billing values, optional quantity, needs with vcpus and memory_gb, spec, and options. It also explains that options are listed by supported_services and gives units for sizes and bandwidth. The customer parameter remains unexplained, which is the main gap.

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 gives a specific verb and resource: starting a quote with a structured requirements list. It distinguishes itself from revise_quote by explaining that exact matches are confirmed automatically while non-exact matches require user review and revise_quote. It is clear, though the opening 'Start a quote' alone would be vague without the requirement details that follow.

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 clearly states the expected workflow: exact matches are auto-confirmed, and non-exact matches should be shown to the user and followed by revise_quote. It also clarifies that nothing is saved on the website, which helps distinguish drafting from publishing. It does not explicitly mention when to use draft_quote versus other quote-related siblings beyond revise_quote, keeping it just short of a 5.

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