Skip to main content
Glama

DMD Costs legal costs tools

CPR costs rules lookup (Parts 3, 25, 36 and 44 to 47)

look_up_cpr_costs_rule
Read-onlyIdempotent

Looks up the costs rules of the Civil Procedure Rules in England and Wales, rule by rule, by number or by words: Parts 44 to 47 (general rules, fixed costs, special cases, detailed assessment), the costs rules of Part 36, costs budgeting and capping in Part 3 and security for costs in Part 25. Each rule comes back with its official heading, Part and Section, a plain-English summary, a practice note, its old number where it was renumbered (2023 and 2025), when it was omitted if it has been, a link to its text on legislation.gov.uk and the free DMD tool for it, if any. A word search works like the page's search box (every word must appear) and returns up to 5 rules. Reference only: it explains the rules and never assesses anyone's costs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "look_up_cpr_costs_rule"
  }
}

Input Schema

NameRequiredDescriptionDefault
ruleNoA rule number, written any usual way: "44.11", "r.47.14", "CPR 3.15A" or "44.2(4)" (the paragraph is not used). An old number the page records is found too, e.g. "25.12" (now 25.26). Give it as text, so "44.10" keeps its 0.
queryNoWords to find, as in the page's search box: a rule has to contain every word, e.g. "default costs certificate", "QOCS" or "interest". Up to 5 rules come back, closest first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond readOnly/idempotent annotations: spells out the returned fields (heading, Part, Section, summary, practice note, old number, omission status, legislation.gov.uk link, DMD tool link), the 5-result cap with closest-first ordering, and the reference-only stance. An agent knows exactly what it gets back and what the tool will not do.

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

Conciseness4/5

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

Purpose is front-loaded and the following sentences cover returns and search behaviour efficiently. The second sentence is a long comma-chained list that is dense but still readable; some of the rule-format detail overlaps with the schema.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so fully, including enrichment fields, renumbering history and external links. Nothing an agent needs in order to invoke it or interpret results is missing.

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% and the schema already documents number formats, old-number resolution, the leading-zero caution and the all-words search semantics. The description restates these without adding new meaning (e.g. no note on what happens if both `rule` and `query` are supplied).

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

Purpose5/5

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

States a specific verb and resource ('looks up the costs rules of the Civil Procedure Rules in England and Wales') and enumerates the exact Parts with their subject matter. Easily distinguished from the calculate_* siblings, which compute rather than explain.

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

Usage Guidelines4/5

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

Explains the two access modes (by rule number or by words) and how word search behaves ('every word must appear', 'up to 5 rules'). The closing 'Reference only: it explains the rules and never assesses anyone's costs' implicitly steers away from the calculation siblings, but no sibling is named and no explicit when-not condition is given.

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