edp-mcp

Official

by UrbanInstitute

Overview Schema Source Related Servers Discussions Admin

Python

Remote

Resolve entity name to ID

resolve_entity

Read-onlyIdempotent

Turn a school, district, or college name into the ID used for data filters. Returns matching candidates with city and level; supply a state FIPS code for schools and districts to avoid ambiguity.

Instructions

Resolve a school/district/college NAME to the ID used in get_data filters.

Returns CANDIDATES with their city and level, not one authoritative answer — names repeat, so the right row is the one whose city and level fit what the user meant. Type words ("Elementary", "High", "ISD") are ignored when matching, which is what lets natural phrasings reach the directory's abbreviations ("Lakewood Elementary" finds "LAKEWOOD EL").

Schools and districts require fips: without it this asks which state rather than guessing, since "Homestead High" exists in CA, WI, IN and FL.

COST: downloads a whole state's directory, so the first call for a state often takes 10-30s and later ones are cached. Resolve names in the same state together.

Args: name: Name to search for; distinctive words matter most. entity_type: "school", "district", or "college" fips: State FIPS code (6 = California). Required for schools and districts. See lookup_codes(format_name="fips"). max_results: Maximum candidates to return (default 15)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`fips`	No
`name`	Yes
`entity_type`	Yes
`max_results`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 18, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already mark readOnly/idempotent/non-destructive; the description adds substantial non-obvious behavior: candidate-style returns, type-word stripping, state-asking rather than guessing, and 10-30s first-call cost with caching. No contradiction.

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

Conciseness5/5

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

The description is long but every sentence carries operational value, with the core task front-loaded and behavior/cost notes structured before Args. No filler or repetition beyond the necessary Args section.

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?

For a 4-parameter resolution tool with an output schema, it covers matching semantics, fips dependency, latency/caching, batching advice, and candidate interpretation. Nothing essential is missing for correct invocation.

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

Parameters5/5

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

Schema description coverage is 0%, but the Args section explains every parameter: name's distinctive-word advice, entity_type's allowed values, fips's conditional requirement and lookup pointer, and max_results default. This fully compensates for the empty schema descriptions.

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?

Opens with a specific verb+resource: 'Resolve a school/district/college NAME to the ID used in get_data filters,' which positions it clearly against get_data and lookup_codes. It also distinguishes itself by stating it returns candidates, not an authoritative answer, because names repeat.

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?

Tells the agent this feeds get_data filters and that fips is required for schools/districts, with a pointer to lookup_codes. It provides clear context but stops short of explicit when-not-to-use/alternative selection among sibling tools.

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

Deploy Server