jean — Molecular Biology & Genomics

rps_blast_cdd

Read-only

RPS-BLAST a protein against NCBI's Conserved Domain Database (CDD) or one of its member collections (Pfam, SMART, COG, KOG, PRK, TIGR, NCBI-curated), through NCBI Batch CD-Search. Returns every domain hit with its hit type (specific, non-specific, superfamily, multi-domain), residue span, E-value, bit score, CDD accession, superfamily cluster and whether the alignment stops short of either end of the model. This is the rpsblast program. Give protein, or give dna to send its six reading frames as six proteins (per-frame CD-Search: each E-value is for its own frame, which is not rpstblastn; rpstblastn_smart runs rpstblastn itself on this machine). The query leaves the machine for NCBI.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`db`	No	the PSSM collection, as the live Batch CD-Search form names it (cdd, cdd_ncbi, oasis_pfam, oasis_smart …); live mode only. Only applies when smode is live.	cdd
`dna`	No	instead of `protein`: DNA whose six reading frames are sent as six proteins, labeled frame +1 … frame -3; each hit names its frame in queryLabel.
`dmode`	No	which hits come back: concise (the best hit per region), standard (the best per source database per region) or full (every hit). Values: rep (concise), std (standard), full (full).	std
`smode`	No	NCBI's search mode: automatic uses precomputed results where they exist, precomputed never runs a search, live always runs one. Only live honours db, evalue and maxhit. Values: auto (automatic), prec (precomputed only), live (live search).	auto
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`evalue`	No	E-value cutoff; live mode only (automatic and precomputed apply 0.01). Only applies when smode is live.
`filter`	No	mask low-complexity regions of the query before searching.
`maxhit`	No	most hits per protein; live mode only (automatic and precomputed apply 500). Only applies when smode is live.
`protein`	No	the protein sequence, one-letter codes; wire it from translate_sequence or read it off a CDS.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`compbasedadj`	No	0 no composition-based statistics · 1 composition-based statistics · 2 composition matrix adjust · 3 forced full matrix adjust.

Output Schema

TableJSON Schema

Name	Required	Description
`hits`	Yes	every domain hit: queryLabel (the frame, for a `dna` query), hitType, pssmId, from, to (1-based residues), evalue, bitscore, accession, shortName, incompleteN, incompleteC, superfamily, definition
`cdsid`	Yes	NCBI's search id, re-openable in CD-Search's own viewer for two days
`count`	Yes	domain hits returned

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld/no-destruct, and the description reinforces egress with 'the query leaves the machine for NCBI' and clarifies mode-dependent behaviour (only live honours db/evalue/maxhit). It stops short of noting auth needs, rate limits, or latency/queuing for the remote service.

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?

Front-loaded with purpose, then usage constraints, then return detail; every sentence is information-dense with no filler. The middle enumeration of return fields is somewhat redundant given an output schema exists, costing a little tightness.

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 an 11-parameter, multi-mode tool with nested objects, the description covers the critical decisions (input type, mode semantics, network egress, sibling disambiguation). Since an output schema exists, the return-value recital is a bonus rather than a gap, though permission/limit context is still absent.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents db, dmode, smode, evalue, maxhit, etc. The prose adds framing (protein or dna, mutual exclusivity, per-frame labeling) but no syntax or semantics beyond what the schema already carries; baseline 3 applies.

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?

States a precise verb+resource (RPS-BLAST a protein against NCBI CDD / member collections via Batch CD-Search) and even identifies the underlying program ('This is the rpsblast program'). It actively distinguishes itself from siblings by naming rpstblastn_smart and clarifying 'which is not rpstblastn'.

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?

Explains the protein-vs-dna choice and what the dna path does (six frames, per-frame E-values), and explicitly routes the agent away from rpstblastn_smart. It does not, however, compare against the closely related rps_blast_smart sibling or state when this local/remote split matters.

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

All jean — Molecular Biology & Genomics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?