Skip to main content
Glama

search_rhea_entity

Find biochemical reactions in the Rhea database by keyword or field-scoped query. Returns reaction equations, EC numbers, ChEBI IDs, and cross-references.

Instructions

Search the Rhea reaction database by keyword and return matching reactions.

Matching is KEYWORD/FUZZY over reaction participants, equations, EC numbers, and cross-references — NOT exact-ID lookup. A term like "glucose" matches any reaction mentioning glucose. Field-scoped terms and wildcards are supported (e.g. ec:1.1.1.1, chebi:17234, uniprot:*). A chebi:-scoped term takes a BARE ChEBI number, not the CHEBI: prefix; a redundant chebi:CHEBI:17234 is auto-corrected to chebi:17234 (the prefixed form otherwise 500s).

RETURNS a dict {'total_count', 'has_more', 'results'} — NOT a bare list. 'total_count' is the number of reactions RETURNED (capped by limit, max 500); 'has_more' is true if more matched beyond the cap. Each result carries the requested columns as snake_cased keys (e.g. 'rhea-id' → 'rhea_id', 'chebi-id' → 'chebi_id'). On upstream failure returns {'error': ...} instead — CHECK FOR 'error' BEFORE READING 'results'.

Valid columns (default rhea-id,equation): rhea-id, equation, chebi, chebi-id, ec, uniprot, go, pubmed, reaction-xref(EcoCyc|KEGG|MetaCyc| Reactome|M-CSA).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNo
termNo
limitNoMaximum number of reactions returned (default 25). Must be between 0 and 500; a negative limit or one above 500 raises ValueError. `has_more` in the result signals whether more matched.
queryNoSearch string, e.g. "ATP", "glucose", "ec:1.1.1.1", "chebi:17234", "uniprot:*". REQUIRED — a blank query raises ValueError (it would otherwise dump an arbitrary slice of the whole database). Accepts aliases: `search`, `term`, `keyword`, `keywords`, `search_term`, `name` (supplying two different values raises ValueError).
searchNo
columnsNoWhich fields to return, as a comma-separated string or a list of column IDs (case-INSENSITIVE). Default "rhea-id,equation". Each requested column becomes a key on every result row; hyphenated IDs are snake_cased in the output (e.g. `chebi-id` → `chebi_id`). The 13 valid column IDs and their output keys: - chebi -> chebi (';'-joined ChEBI names) - chebi-id -> chebi_id (';'-joined ChEBI ids) - ec -> ec (';'-joined EC numbers) - equation -> equation (textual reaction equation) - go -> go (GO id + label) - pubmed -> pubmed (';'-joined PubMed ids) - reaction-xref(EcoCyc) -> xref_ecocyc - reaction-xref(KEGG) -> xref_kegg - reaction-xref(M-CSA) -> xref_mcsa - reaction-xref(MetaCyc) -> xref_metacyc - reaction-xref(Reactome) -> xref_reactome - rhea-id -> rhea_id (e.g. RHEA:10000) - uniprot -> uniprot (count of annotated UniProtKB entries) An unknown column raises ValueError — the API would otherwise silently drop it and return an unannounced narrower table.rhea-id,equation
keywordNo
keywordsNo
search_termNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

With no annotations, the description carries full burden and excels: it details return format (dict with total_count, has_more, results), error handling (upstream failure returns error dict), column naming conversion (snake_case), auto-correction of ChEBI prefix, and multiple error conditions (blank query, unknown column, negative limit).

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 long but well-structured with paragraphs and bullet points. Every sentence adds value, and it front-loads the purpose. A minor reduction for length, but given the complexity it is appropriate.

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?

Despite having no annotations and 9 parameters, the description covers input, behavior, output, and errors in detail. It explains the return format, column mapping, and all edge cases, making it self-contained.

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 coverage is only 33%, but the description compensates comprehensively. It explains the 'query' parameter in depth, lists all valid columns and their output keys, describes the 'limit' parameter behavior, and documents multiple aliases for the query parameter.

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 clearly states the tool searches the Rhea reaction database by keyword and returns matching reactions. It explicitly distinguishes itself from exact-ID lookup tools, which separates it from sibling search tools like search_uniprot_entity.

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 explains when to use it (keyword/fuzzy search) and provides examples of field-scoped terms. It explicitly states it is NOT for exact-ID lookup, giving implicit guidance on when not to use. However, it does not name alternative tools for exact lookup.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dbcls/togomcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server