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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: it discloses the two-step validation/confirmation flow, that a confirmation token is returned in step 1 and must be passed in step 2, that the enquiry is only submitted after step 2, that an email with a required click-link is sent, and that no provider sees the enquiry until the link is clicked. It also defines the exact consent semantics. This is exceptional transparency for a mutation tool.

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 dense but well-structured, front-loading the core purpose and the two-step process in a logical order. Every sentence carries necessary information, though the consent line repetition (in the description and again in the schema) is slightly redundant. It is appropriately sized for the complexity of a two-step, consent-driven submission tool.

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?

Given the complexity of a two-step submission with consent and email confirmation, the description is complete: it explains the full flow, the role of the confirmation token, the consent requirement, and the post-submission email step. No output schema exists, but the description mentions what step 1 returns (a summary, consent line, and confirmation token) and what happens after step 2 (email sent, provider visibility gated). An agent has everything needed to invoke this tool correctly.

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 schema already documents the parameters, setting a baseline of 3. The description adds operational context beyond the schema: answers are 'keyed by field key from enquiry_fields', the confirmation token comes specifically from step 1 after the person approved the summary, and consent=true has a precise meaning tied to the displayed line. These details help an agent use the parameters correctly across the two-step flow, though the schema already covers the basic types and requirements.

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 title and description both specify the verb and resource ('Submits an enquiry') and add critical scope: 'to SEO for plumbers', 'NOT a purchase, NOT a guaranteed quote'. This explicitly distinguishes it from the sibling enquiry_describe and enquiry_fields tools, which are clearly read-only helpers. The two-step flow is front-loaded and unambiguous.

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 description lays out an explicit when-to-use sequence: Step 1 call with answers and consent=true; Step 2 only if the person agrees, call again with the same answers, consent=true and the confirmation token. It also states the prerequisite for consent (the person has read and agreed to the specified line) and the post-submission requirement (the person must click an email link before any provider sees it). No alternative tools are needed for this specific action, and the exclusion 'NOT a purchase, NOT a guaranteed quote' further clarifies scope.

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