Skip to main content
Glama

rank_schools

Read-onlyIdempotent

Rank state-funded mainstream schools in England, or in one local authority, on a single published measure. Measures: ks2.rwm_expected_percent (Year 6: expected standard in reading, writing and maths; primary), ks2.rwm_higher_percent (Year 6: higher standard in reading, writing and maths; primary), ks4.attainment8 (GCSE: Attainment 8; secondary), ks4.progress8 (GCSE: Progress 8; secondary), ks4.engmath_grade5_percent (GCSE: grade 5 or above in English and maths; secondary), ks5.alevel_aps_per_entry (A level: average points per entry; secondary), ks5.alevel_value_added (A level: value added; secondary), absence.overall_percent (Attendance: overall absence (lowest first); primary and secondary), absence.persistent_percent (Attendance: persistent absence (lowest first); primary and secondary), admissions.first_preferences_per_offer (Demand: first preferences per place; primary and secondary). A single-measure ranking reflects the pupils a school admits as well as its teaching.

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": {
      "measure": "<measure>"
    },
    "name": "rank_schools"
  }
}

Input Schema

NameRequiredDescriptionDefault
townNoPostal town (such as Huddersfield) with five or more schools; give county too where the name repeats
limitNoNumber of schools from the top, 1 to 100 (default 25)
phaseNoprimary or secondary; defaults to the measure's phase
countyNoCeremonial county (such as West Yorkshire) instead of a local authority
measureYesMeasure ID, for example ks4.attainment8 or ks2.rwm_expected_percent
local_authorityNoLocal authority name (such as Leeds) or code; leave out for all of England
exclude_selectiveNoLeave out grammar schools, which select pupils by ability

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / county
      Added value: +{
      +  "description": "Ceremonial county (such as West Yorkshire) instead of a local authority",
      +  "type": "string"
      +}
    • addedInput schema / properties / town
      Added value: +{
      +  "description": "Postal town (such as Huddersfield) with five or more schools; give county too where the name repeats",
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world behavior. Beyond that, the description adds meaningful scope and interpretation context: it limits the tool to state-funded mainstream schools, notes geography options, and warns that a single-measure ranking reflects intake as well as teaching. It does not cover rate limits, failure behavior, or output shape.

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 purpose is front-loaded and the long measure catalog is necessary because measure is required and the schema has no enum. The catalog is a dense run-on list rather than a structured list, but it contains little waste and the closing caveat is valuable.

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?

For a seven-parameter ranking tool with full schema coverage and annotations, the description covers scope, measure selection, and an important interpretive caveat well. It leaves gaps on explicit sibling routing and on what a ranked response contains, which matters somewhat because there is no output schema.

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

Parameters4/5

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 substantially strengthens the required measure parameter by enumerating ten valid measure IDs with definitions, associated phases, and, for absence measures, 'lowest first' ranking direction. The other parameters are largely left to the schema.

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 opens with a specific verb and resource: 'Rank state-funded mainstream schools in England, or in one local authority, on a single published measure.' It also enumerates the supported measures and their phases. It does not explicitly name sibling tools such as compare_schools or find_schools, so it stops short of full sibling differentiation.

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 by 'Rank ... on a single published measure' and the list of measures, but there is no explicit when-to-use/when-not guidance or named alternative. An agent must infer that this is for leaderboard-style ranking rather than per-school comparison, search, or inspection 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