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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real behavior beyond that: the precision field indicates which search variant ran, totals already include intro pricing, post-intro rises and setup fees, and the output must be presented verbatim without re-ranking or recalculation.

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?

Front-loaded with the trigger condition, then workflow, then output rules, then follow-up — a sensible progression. It is long and slightly repetitive ('translate the user's needs into the filter inputs' and 'refine with the filter inputs' restate the same idea), but nearly every sentence carries an operational instruction.

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 9-parameter open-world search with an output schema and annotations already in place, this description covers the full loop: prerequisite, fallback, parameter pairing, output handling constraints, and next-step refinement. Nothing an agent needs before or after the call is missing.

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% and the schema already carries the per-parameter meaning, including the speed-translation examples, so the baseline is 3. The description only marginally extends this with the uprn/address_label pairing instruction and the generic 'translate needs into filter inputs' directive.

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 first sentence states a specific verb (find), resource (broadband deals/offers/packages) and scope (available where they live), and it explicitly names the sibling search_addresses as the upstream step. An agent can distinguish this from check_if_overpaying and get_deal_details without opening any 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?

Explicit routing rules: call search_addresses first if no address is picked, fall back to postcode-only when the user declines or no addresses are found, pass address_label alongside uprn once picked. It also prescribes the post-presentation follow-up, so both entry and continuation conditions are covered.

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