One MTD answer in full: the question, the short answer, the complete plain-text body, the FAQ pairs, and every GOV.UK/HMRC source page the answer rests on. Use the slug from search_mtd_answers.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Answer slug, e.g. 'mtd-deadlines', 'who-has-to-use-mtd-in-2026'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the full return contract—question, short answer, body, FAQ pairs, and source pages—which makes behavior predictable. It does not cover auth, error cases, or side effects, but for a read-only get-by-slug tool this is a reasonable disclosure.
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?
Two sentences with no filler. The first sentence front-loads everything the agent needs to know about the return value, and the second sentence gives the critical input source. Every word earns its place.
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 simple one-parameter retrieval tool with no output schema, the description is largely complete: it defines what is returned, how to obtain the required slug, and the relationship to the sibling search tool. The only gap is unspecified error behavior, which is minor here.
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?
The schema already documents the slug parameter with examples at 100% coverage. The description adds meaning beyond the schema by specifying that the slug must come from search_mtd_answers, which clarifies provenance and avoids arbitrary slug guesses.
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 names a specific verb and resource: retrieving one MTD answer in full. It enumerates the answer's complete contents (question, short answer, plain-text body, FAQ pairs, source pages) and explicitly differentiates from search_mtd_answers by requiring its slug.
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 instruction 'Use the slug from search_mtd_answers' gives a concrete prerequisite and workflow, effectively telling the agent when this tool is appropriate: after locating an answer via the sibling search tool. It does not explicitly state when not to use it, but the contrast with search_mtd_answers is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools overlap in subject matter: borough_odds, violation_dismissal_rates, and plate_lookup all touch NYC hearing outcomes, while operator_route_lookup and popla_outcomes both expose POPLA operator records. The descriptions are detailed enough to separate them on close reading, but an agent could easily select the wrong one when asking for odds or appeal outcomes.
The names are uniformly lowercase snake_case and readable, but the pattern is mixed: get_mtd_answer, list_doors, and search_mtd_answers use a verb_noun form, while borough_odds, popla_outcomes, and violation_dismissal_rates are noun phrases, and plate_lookup/operator_route_lookup use noun_lookup compounds. There is no single consistent naming convention across the set.
Nine tools is within the ideal range and each tool represents a distinct, substantive data product or query endpoint. For a gateway spanning multiple domains, this is well-scoped and not bloated.
The main query surfaces are covered: NYC parking has plate, borough, and violation-type views; UK parking has operator routing, deadline calculation, and POPLA outcomes; and MTD has search plus full-answer retrieval. Minor gaps exist, such as IAS appeal outcomes and a way to list all MTD answers without searching, but these are workable rather than blocking.