Skip to main content
Glama

Search Structures

search_structures
Read-onlyIdempotent

Search the Crystallography Open Database (COD), an open repository of crystal structures (inorganic, organic, metal-organic, and mineral). Search by compound name (free text), chemical formula, or mineral name; returns matching crystal structures with unit-cell parameters, space group, year, and a link to the CIF structure file. Keyless. Provide at least one of query, formula, or mineral. Formulas are normalized to COD's stored Hill notation for you, so "NaCl", "SiO2" and "CaCO3" all work; the response reports formula_searched with the exact string that was matched.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax structures to return (default 20, max 100).
queryNoFree-text search (compound/common name, title words, author, etc.). e.g. "quartz", "aspirin".
formulaNoChemical formula in any common spelling — "NaCl", "SiO2", "CaCO3", "C6H6", or COD's own "O2 Si". It is converted to COD's stored Hill form (C first, then H, then the rest alphabetically; counts of 1 omitted) before searching. Matches the whole stoichiometry exactly, so "SiO2" will not match "CaMgSi2O6".
mineralNoMineral name, e.g. "Quartz", "Calcite", "Halite". Matched against each structure's mineral field (case-insensitive substring), so "Quartz" also returns "Quartz low" / "Quartz high".

TDQS

A4.3/5.0
Behavior4/5

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

Annotations indicate readOnly, openWorld, idempotent, not destructive. Description adds details: formula normalization, exact stoichiometry matching, case-insensitive substring for mineral, and reporting of formula_searched. No contradictions.

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?

Description is well-structured, front-loaded with purpose, then details. Consists of 4 sentences with no waste. Could be slightly more concise but effective.

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?

Covers input requirements, parameter semantics, return fields, and normalization behavior. No output schema but description provides enough context. Minor gap: no mention of pagination or error handling.

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 baseline is 3. Description adds significant value: explains formula normalization behavior, matching rules, and that query is free-text. Mineral parameter description clarifies substring matching.

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?

Clearly states it searches the Crystallography Open Database by compound name, formula, or mineral name, returning crystal structures with specific parameters. Distinguishes itself from siblings like get_cif and get_structure by being a search tool.

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?

Explicitly states 'Keyless' and that at least one of query, formula, or mineral must be provided. Provides examples of inputs. Could be improved by mentioning when to prefer siblings, but contextually clear.

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.

TDQS

A3.7/5.0
Disambiguation2/5

There are three overlapping ask_pipeworx variants (stable, beta, grounded) plus a dense cluster of six polymarket trading/arbitrage tools, making misselection likely. Several other tools also blur together around research aggregation and entity lookup (entity_profile, compare_entities, recent_changes, validate_claim).

Naming Consistency3/5

All tool names are lowercase and snake_case, but the pattern is inconsistent: some are verb_noun (get_structure, resolve_entity), some are noun phrases (recent_changes, polymarket_edges), and a few are bare verbs (remember, forget, recall). The ask_pipeworx_beta/ask_pipeworx_grounded suffix pattern is readable but not mirrored across the rest of the set.

Tool Count2/5

34 tools is above the 25+ threshold for a server whose stated purpose is Crystallography, and only 3 of those tools actually serve that domain. The rest belong to Pipeworx data lookup, Polymarket betting, memory, research, subscriptions, and unrelated utilities, so the count feels excessive and the scope is unclear.

Completeness3/5

As a broad data-research toolset, there is decent lifecycle coverage: lookup, research, grounded verification, entity resolution, comparison, subscriptions, feedback, and memory all exist. However, for a server named Crystallography the domain surface is thin (search/get/get CIF only), and there is no general web-search fallback for topics not in the structured catalog.