Skip to main content
Glama

DMD Costs legal costs tools

Costs order decoder (PD 44 para 4.2 and the deemed orders)

explain_costs_order
Read-onlyIdempotent

Explains what a costs order in England and Wales means, from the words of the order or the wording picked from a list: costs in any event, costs in the case or in the application, costs reserved, claimant's or defendant's costs in the case, costs thrown away, of and caused by, here and below, no order as to costs, summary and detailed assessment, payment on account, indemnity or standard basis, an order silent on costs, deemed orders (Part 36 acceptance, discontinuance, strike-out for an unpaid fee), wasted costs and non-party costs. Says who recovers the costs under each way the case can end, whether anything is payable now and how the amount is decided, with the rule, and how family proceedings and employment tribunals differ. It explains: it never puts a figure on 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": "explain_costs_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoThe date the order was made, for the date a stated sum is due.
pickNoInstead of text, the wording: "costs" (costs, or costs in any event), "in-the-case", "in-the-application", "reserved", "own-in-the-case" (claimant's or defendant's costs in the case), "thrown-away", "of-and-caused-by", "here-and-below", "no-order", "summary" (a sum stated in the order), "detailed" (to be assessed if not agreed), "immediate" (assessed immediately or forthwith), "on-account", "proportion" (a share of the costs), "indemnity", "standard", "silent" (the order says nothing about costs), "part36" (Part 36 offer accepted), "discontinuance", "fees-strike-out" (struck out for an unpaid fee), "wasted", "non-party", "preparation-time" (employment tribunal), "follow-the-event".
textNoThe words of the order about costs, e.g. 'Costs of the application reserved. Otherwise, costs in the case.' Names and sums can be left out.
forumNoThe kind of proceedings (default civil): "civil" (Civil (CPR)), "family" (Family (FPR)), "tribunal" (Employment tribunal).
partyNoWho has the benefit of the order, to make the answer specific. Leave out to use the party the order names.
specialNoSpecial cases that apply: "qocs" (A personal injury claim (QOCS)), "legalAidReceiving" (The party receiving costs is legally aided), "legalAidPaying" (The party paying costs is legally aided), "child" (A child or protected party is involved), "lip" (A litigant in person receives the costs), "frc" (A fixed recoverable costs claim), "smallClaims" (The small claims track).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / date / description
      Previous value: -"The date the order was made, for the date a stated sum is due (YYYY-MM-DD)."New value: +"The date the order was made, for the date a stated sum is due."
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive behaviour, but the description adds substantial context beyond them: it says the tool reports who recovers costs under each ending, whether anything is payable now, how the amount is decided, the relevant rule, and how family and tribunal proceedings differ. The explicit limitation that it never puts a figure on costs prevents a common misuse expectation and is exactly the kind of behavioural disclosure that helps an agent invoke it correctly.

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?

The description is front-loaded with the core purpose and the final sentence usefully states the key limitation. However, it is a single long run-on sentence that enumerates every order type and partially duplicates the pick enum already in the schema, which slightly reduces conciseness. It remains efficient enough for a decoder with broad coverage.

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?

Given the tool's complexity—six optional parameters, three enums, and no output schema—the description covers what is explained, the range of supported order types, the cross-jurisdiction differences, and the explicit non-calculation boundary. Nothing essential for an agent to call it correctly 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 description coverage is 100%, so the schema already fully documents all six parameters, including the pick enum, text, forum, party, and special cases. The description repeats the idea of using order text or a picked wording but adds no meaningful parameter-level detail beyond the schema—for example, it does not explain how date, party, or special interact with the answer. The baseline 3 is appropriate.

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?

The description opens with a specific verb and resource ('Explains what a costs order in England and Wales means') and then enumerates the exact order wordings supported, so an agent can immediately tell this is a decoder rather than a calculator or rule lookup. It distinguishes itself from sibling tools like calculate_fixed_costs or look_up_cpr_costs_rule by describing what it explains and how it uses the order wording.

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?

The description clearly frames usage: the tool works 'from the words of the order or the wording picked from a list,' which tells the agent when this tool is appropriate. It also sets a boundary with 'It explains: it never puts a figure on costs,' implicitly steering numeric questions elsewhere, though it does not explicitly name alternative siblings for calculation or rule lookup.

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