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

With no annotations, the description carries the full burden, and it does substantial work: it discloses the validation/return behavior of step 1 (summary, consent line, confirmation token), the irreversibility gate (nothing is submitted until step 2), the double opt-in email link, and the third-party data sharing scope. What it omits is failure behavior (what happens on invalid answers or a stale/incorrect token) and any indication of whether step 1 has side effects on the server.

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?

It is front-loaded with the most load-bearing fact ('NOT a purchase') and is organized as Step 1 / Step 2, which mirrors how the agent must call it. The verbatim consent paragraph is long and duplicates the consent parameter description almost word for word, which is the one place length is not fully earned.

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 two-phase, human-in-the-loop, third-party-disclosing tool with no output schema and no annotations, the description supplies nearly everything an agent needs: sequencing, the confirmation token's provenance, the consent text, and what happens after submission. The remaining gap is error/recovery handling for an invalid token or failed validation.

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, but the description adds real semantics beyond the schema: answers must be keyed by field key sourced from enquiry_fields, and 'confirmation' is specifically the step-1 token accepted only after the person approves the summary. That ordering constraint is not encoded anywhere in 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?

It states a specific verb and resource ('Submits an enquiry to Notice Period Calculator') and immediately draws the boundary that matters most: 'NOT a purchase, NOT a guaranteed quote.' It also points at the sibling that supplies the input shape ('keyed by field key from enquiry_fields'), so an agent can distinguish it from calculate/enquiry_describe without opening a schema.

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 the exact call sequence: step 1 with answers and consent=true, step 2 only 'if the person agrees' with the confirmation token added. It gives an explicit gate for the second call and explains the human-facing obligation (show the summary and consent line) before re-invoking.

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