Skip to main content
Glama

Dental prices and NHS places near a postcode

find_dentist
Read-onlyIdempotent

What practices near a London postcode district charge for a treatment, lowest first, read by hand from each practice's own price list, with the NHS charge and which nearby practices say they are taking new NHS patients. Covers Tower Hamlets, Hackney, Southwark, Newham, City of London, Islington, Lewisham, Waltham Forest, Haringey, Redbridge, Greenwich, Barking and Dagenham, Lambeth, Camden, Bexley, Westminster, Kensington and Chelsea, Hammersmith and Fulham, Wandsworth, Barnet, Enfield, Bromley, Havering, Brent, Ealing, Harrow, Croydon, Sutton, Merton, Hounslow, Hillingdon, Richmond upon Thames and Kingston upon Thames so far. Every price carries its source page and the date it was read. Always pass on the urgent-care line.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "postcode": "<postcode>",
      "treatment": "<treatment>"
    },
    "name": "find_dentist"
  }
}

Input Schema

NameRequiredDescriptionDefault
postcodeYesThe first half of a UK postcode (the district), e.g. "E14" or "EC1M". Send only that: a full postcode works but only the first half is used.
max_milesNoHow far from the middle of the district. Default 2, the same as toothache.fyi's treatment pages. 1 is walking distance, 6 a short drive.
max_priceNoBudget in pounds. Optional.
treatmentYesWhat the person needs. "emergency" for pain now; "checkup" if unsure; "implant" means the implant and its crown for one tooth.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / treatment / description
      Previous value: -"What the person needs. \"emergency\" for pain now; \"checkup\" if unsure."New value: +"What the person needs. \"emergency\" for pain now; \"checkup\" if unsure; \"implant\" means the implant and its crown for one tooth."
    • changedInput schema / properties / treatment / enum
      Previous value: -[
      -  "checkup",
      -  "emergency",
      -  "hygiene",
      -  "filling",
      -  "extraction",
      -  "rootcanal",
      -  "crown",
      -  "whitening"
      -]New value: +[
      +  "checkup",
      +  "emergency",
      +  "hygiene",
      +  "filling",
      +  "extraction",
      +  "rootcanal",
      +  "crown",
      +  "whitening",
      +  "implant"
      +]
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-open-world behavior, but the description adds substantive context the annotations cannot: prices are transcribed by hand from each practice's own price list, every price carries its source page and read date, and coverage is limited to a named list of boroughs. That provenance and coverage disclosure is exactly the kind of thing an agent needs before presenting results as authoritative. It is weakened by the trailing 'Always pass on the urgent-care line', which is ambiguous and sits oddly at the end.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is a long run-on that chains pricing, NHS charge and new-patient status together, and the 32-borough enumeration consumes roughly half the text. The coverage list does earn some of its space, but the final sentence about the urgent-care line is unexplained and reads as a fragment from an external source.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does useful work describing what comes back: prices ordered lowest first, the NHS charge, new-patient status, and per-price source and read date. It also bounds geographic coverage. What is missing is what happens for a postcode outside the covered boroughs or when no practices match, which matters for a lookup tool that advertises a finite area list.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description's additions (sorted lowest first, NHS charge alongside private price) are about output rather than parameter meaning. The treatment guidance ('implant means the implant and its crown for one tooth') duplicates what the schema already says. No new interpretation of postcode, max_miles or max_price is offered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource: it returns practices near a London postcode district with per-treatment prices, the NHS charge, and which practices report taking new NHS patients. That is far more specific than the title. It never names or differentiates itself from the nhs_charges sibling, so routing between the two is left to the agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: postcode district plus a treatment yields a price comparison, and the treatment enum guidance ('emergency for pain now', 'checkup if unsure') helps pick the right call. There is no explicit when-to-use/when-not-to-use statement and no mention of nhs_charges as the alternative for pure NHS charge lookups.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources