NEMAD MCP

nemad_search

Read-only

Search the Northeast Materials Database by comma-separated elements, optionally requiring an exact element match, and cache paginated results for reading with a separate results tool.

Instructions

Search NEMAD by comma-separated elements (for example Fe,Co), then cache results.

exact_match requires exactly those elements. limit is 1..1000, or -1 for all results subject to the response-size bound. Use nemad_read_results to read pages.

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": {
      "database_type": "<database_type>",
      "elements": "<elements>"
    },
    "name": "nemad_search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`elements`	Yes
`exact_match`	No
`database_type`	Yes

Output Schema

Name	Required	Description	Default
`count`	Yes	Matches NEMAD returned, capped by limit; not the database total.
`cache_key`	Yes
`next_step`	No		Call nemad_read_results with cache_key to read a page of results.
`database_type`	Yes
`results_returned`	Yes
`expires_in_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds genuinely non-structured behavior: results are cached server-side, and the limit of -1 returns all results 'subject to the response-size bound', which warns the agent about truncation. It does not state cache lifetime or whether repeated searches are deduplicated, which keeps it from a 5.

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 search mode and input format are front-loaded, then the exact_match and limit semantics follow in order of decision importance, ending with the pointer to the read tool. Every sentence conveys a distinct constraint; there is no filler, restatement of the tool name, or redundant phrasing.

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?

An output schema exists, so the description need not explain return values, and it correctly focuses on the query format, the exactness toggle, the limit bound including the -1 special case, and the paging handoff. What is missing is only the meaning of the database_type dimension and any note on how to interpret the cached result handle, which is a modest gap for a 4-parameter read tool.

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 description coverage is 0%, so the description must carry the load, and it covers three of four parameters with real semantics: elements as a comma-separated list with an example, exact_match as requiring precisely those elements, and limit as 1..1000 or -1 for all. database_type is left to its enum values, which are largely self-explanatory, so the gap is minor rather than disqualifying.

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?

States a specific verb and resource ('Search NEMAD by comma-separated elements') and immediately gives a concrete input example (Fe,Co), so the agent knows the search domain. It partially distinguishes itself from the sibling read tool by deferring page retrieval to nemad_read_results, but it never clarifies how it differs from nemad_formula_search, leaving one sibling ambiguous.

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?

One explicit routing rule is given: 'Use nemad_read_results to read pages', which tells the agent the follow-up step. However, there is no guidance on when this element-based search is preferable to nemad_formula_search, and no prerequisites or exclusions are mentioned, so usage must be inferred from parameter semantics.

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

Deploy Server