Skip to main content
Glama

jean — Molecular Biology & Genomics

check_rows

Read-only

A QC gate over a TABLE: assert something about every row at once (every band inside a size window, no guide above an off-target score, at least three assays under a penalty). Fails the pipeline (so everything downstream skips) and names the rows that broke the rule.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxNoupper bound, inclusive. Only applies when operator is between.
minNolower bound, inclusive. Only applies when operator is between.
setNothe values the field must be one of (or none of). Only applies when operator is in or not_in.
textNothe text the field must contain. Only applies when operator is contains.
countNoN, for the counted requirements. Only applies when require is at_least or at_most or exactly.
fieldNowhich field of each row to test (e.g. `size`, `score`). Leave empty when the rows are plain numbers.
itemsYesthe rows to check. Wire a json/list output (bands, guides, assays, amplicons).
labelNowhat this gate is checking, in your words. It becomes the message when it fails.
valueNothe value to compare against. Only applies when operator is == or != or > or >= or < or <=.
_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.
recordNooptional: the record this gate is guarding. It comes back out of `record` when the check passes, so the gate sits in the middle of a chain.
requireNowhat must hold across the table. Values: all (every row), any (at least one row), none (no row), at_least (at least N rows), at_most (at most N rows), exactly (exactly N rows).all
_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.
operatorNohow each row is compared. Values: == (equals), != (does not equal), > (greater than), >= (at least), < (less than), <= (at most), between (between (inclusive)), in (is one of), not_in (is none of), contains (contains text), is_true (is true), not_empty (is not empty).>=
report_onlyNoreport the verdict instead of stopping the run: wire `passed` (or `failed`) into another step's condition to choose a branch.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
failedYesthe opposite verdict, so the ELSE arm of a branch needs no extra step. Only meaningful with `report_only` on
passedYeswhether the requirement held. As a gate this is true whenever it is read downstream; with `report_only` on it is the real verdict, for driving a branch
recordYesthe guarded record, unchanged. Wire it into the next node's $subject to make that step conditional
matchedYeshow many rows met the per-row condition
messageYeswhat was checked, in words
offendersYesthe rows that did NOT meet it: what to look at when the gate fails

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint/destructiveHint=false, but the description adds a genuinely non-obvious trait: a failed check halts the pipeline so everything downstream skips, and the failure message names the offending rows. This control-flow behavior is not derivable from the annotations, and the record passthrough expectation is also useful context.

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?

Three tightly packed sentences: the first defines the gate, the second gives illustrative predicates, the third states the failure semantics. The core purpose is front-loaded and nothing is wasted, though the parenthetical examples list is slightly long.

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 15-parameter, nested-schema tool with an output schema present, the description supplies the essential mental model (row-set gate, fail-halts-pipeline, failing rows reported) without needing to restate return values. It could be more complete by noting the report_only alternative behavior, but overall it is sufficient to invoke correctly.

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 coverage is 100%, so the schema already documents all 15 parameters including the operator/require enums and conditional min/max/set/text/value semantics. The description's predicate examples map loosely onto these concepts but add no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

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 states a specific verb and scope: assert a predicate over every row of a table at once, with concrete examples (size window, off-target guide score, assay count). It clearly distinguishes this aggregate gate from a per-value check, though it never names a sibling like check_value, check_invariants, or filter_items.

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 implied rather than stated: as a 'QC gate' it sits mid-pipeline and skips downstream steps on failure, and the record passthrough hints at chaining. There is no explicit when-to-use vs alternatives guidance (e.g. when to prefer check_rows over filter_items or summarize_rows), and no mention of the report_only branching mode in prose.

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