Skip to main content
Glama

design_codon_tiling_primers

Read-only

Codon-tiling mutagenesis primers for a whole CDS: one primer per codon, each carrying a degenerate codon (NNN/NNK/NNS/NNC/NNG) at its centre, with the flanks grown or shrunk so every primer lands inside a Tm window (jbloomlab CodonTilingPrimers).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "design_codon_tiling_primers"
  }
}

Input Schema

NameRequiredDescriptionDefault
cdsNothe CDS to tile, in frame. Left empty the record's `cds_feature`, or the selection, is tiled and the flanking bases come from the record around it.
_filesNoThe 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.
flanksNowith a literal `cds`: the bases either side of it, as `5'flank,3'flank`. Upstream anneals every primer in these, so without them a tiled primer has nothing to grow into — give at least `(primer_length - 3) / 2` bases per side. Advanced.
prefixNoprefix for the generated primer names. Advanced.tile
_subjectNoThe 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.
tm_modelNoTm scale the window is judged on. Upstream tiles against Biopython's nearest-neighbour Tm, which is `santalucia` here. Values: santalucia (SantaLucia nearest-neighbor (Biopython Tm_NN defaults)), wallace (Wallace rule (4 °C per G·C, 2 °C per A·T)), gc:Chester_1993 (GC formula: Marmur-Doty (Chester & Marshak 1993)), gc:QuickChange (GC formula: QuikChange (the kit manufacturer’s own formula)), gc:Schildkraut_1965 (GC formula: Schildkraut & Lifson 1965 (Marmur-Doty + log[Na⁺])), gc:Wetmur_Melting_1991 (GC formula: Wetmur 1991, DNA (MELTING 4.3 approximate mode)), gc:Wetmur_RNA_1991 (GC formula: Wetmur 1991, RNA), gc:Wetmur_DNA_RNA_1991 (GC formula: Wetmur 1991, RNA/DNA hybrid), gc:Primer3 (GC formula: Primer3Plus product Tm (Biopython’s default set)), gc:Ahsen_2001 (GC formula: von Ahsen 2001 (accuracy against ease of use)).santalucia
max_lengthNolongest primer it may grow to. In nt. Advanced.
min_lengthNoshortest primer the flank search may shrink to. In nt. Advanced.
cds_featureNotile this annotated CDS of the open record by NAME, on its own strand, exactly as `codon_usage_analysis` takes one. The flanks come from the record either side of it.
first_codonNothe number given to the first codon in primer NAMES. Set it when the CDS you are tiling starts part-way through a protein. Advanced.
max_primer_tmNohighest acceptable primer Tm; must be above `min_primer_tm`. In °C.
min_primer_tmNolowest acceptable primer Tm. In °C.
primer_lengthNostarting primer length, in bases. Must be ODD: the flanks are (n-3)/2 per side. Upstream's own default. In nt.
ambiguous_codonNothe degenerate codon installed at every position. NNK and NNS halve the stop codons NNN introduces; NNC and NNG are narrower still.NNN

Output Schema

NameRequiredDescriptionDefault
countYesprimers designed, which is the number of codons tiled
codonsYescodons in the tiled CDS
primersYesone row per codon: name, seq (with the degenerate codon at its centre), length, tm, codonIndex, and `start`, the 0-based offset in the tiled string
tmRangeYesthe lowest and highest Tm actually achieved, against the window asked for: `{ min, max, wanted: { min, max } }`
outsideWindowYesprimers whose Tm the flank search could not bring inside the window within the length limits. Reported rather than dropped

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description goes further by disclosing the design algorithm itself – flanks 'grown or shrunk' so every primer lands in a Tm window, and attribution to the jbloomlab CodonTilingPrimers implementation. That implementation reference is genuinely useful for predicting output. It omits any note on computational cost or output structure, but the output schema is present, so a 4 is fair.

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?

It is a single front-loaded sentence that states purpose first, then mechanism, then provenance – nothing is redundant. The dense parenthetical at the end is slightly awkward but earns its place by grounding the tool in a known implementation.

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 a 14-parameter tool with nested objects, an output schema and full annotation coverage, the description supplies the conceptual model (per-codon degenerate primers sized into a Tm window) that ties the many advanced parameters together. The remaining details – flank requirements, prefix, first_codon numbering – are fully documented in the schema, so nothing critical is missing, though explicit sibling routing would complete it.

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% and the parameter descriptions already explain primer_length parity, min/max_length semantics, Tm window ordering and degenerate codon choice. The description only echoes the degenerate codon options and the Tm-window mechanism already documented per-parameter, so it adds little new meaning. Baseline 3 applies when the schema does the heavy lifting.

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?

The description names a specific verb and resource ('Codon-tiling mutagenesis primers for a whole CDS') and pins down the exact output shape: one primer per codon, each with a degenerate codon (NNN/NNK/NNS/NNC/NNG) at its centre. That is far more than a restatement of the name and lets an agent recognise the codon-saturation use case. It does not explicitly contrast itself with close siblings like design_saturation_primers or design_mutagenesis_primers, so it stops short of a 5.

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?

Usage is only implied: the description makes clear this is for tiling an entire CDS with degenerate codons, which signals the scenario, but it never says when to choose this over design_saturation_primers or design_mutagenesis_primers, nor any prerequisites or exclusions. The agent must infer the alternative from the mechanism description alone.

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.

Resources