Ravelry MCP Server

Check stitch counts

count_stitches

Read-onlyIdempotent

Counts stitches in knitting and crochet pattern rows, flagging skipped stitches or totals that differ from the printed pattern. Use it to walk through a row or check instructions for errors.

Instructions

Reads written knitting or crochet instructions row by row ("*k2, p2; rep from * to last 2 sts, k2", "(sc, inc) x 6 (18)") and counts the stitches each step uses and makes. Flags rows that do not use every stitch and counts that differ from the one printed in the pattern. Use it to walk someone through a row or to check a pattern for errors.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	Yes	Consecutive rows or rounds, one per item, as written in the pattern.
`craft`	No		knitting
`stitches_before`	No	Stitches on the needle before the first row (0 for a magic ring).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	Yes
`problems`	Yes	Rows with at least one warning.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.8.0Oct 6, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds that the tool flags rows not using every stitch and flags count mismatches, which is real behavioral detail beyond the annotations. Output schema exists so return-format details are rightly left out.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool reads, followed by what it flags and when to use it. The inline examples earn their space by showing the input format. Zero waste.

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?

Annotations cover safety, output schema covers returns, and the description covers input format with examples plus flag behavior. Nothing essential is missing for an agent to call this correctly across knitters and crocheters.

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 67%. The description does not mention the rows, craft, or stitches_before parameters by name, though the row-by-row input model is conveyed implicitly through examples. With a reasonably descriptive schema, baseline 3 is appropriate.

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 specific verb (reads/counts), resource (written knitting/crochet instructions row by row), and even gives concrete input examples like '*k2, p2; rep from * to last 2 sts, k2'. It also names the two output behaviors (flags rows missing stitches, mismatched counts), distinguishing it from siblings like spread_evenly or adjust_for_gauge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states two use contexts: walking someone through a row and checking a pattern for errors. No other sibling is named as an alternative, but the two usage modes are clear enough that an agent knows when to invoke this versus counting manually or using spread_evenly.

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

Deploy Server