Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

origami_rows

Rows of an Origami table — read them (flat {slug: value} rows, following the cursor) or upsert them (the ONLY write path for rows).

op:

  • "list": {count, total, pages_fetched, cursor, truncated, items}. Pages are 50 rows (limit ≤ 200); the server follows nextCursor up to max_pages (cap 20). truncated: true + cursor = there is more — call again with that cursor.

  • "upsert" (WRITE): rows (1–100 dicts keyed by input-column SLUG) matched on match_columns — a row whose match values all equal an existing row UPDATES it, otherwise it is INSERTED. Slugs come from origami_tables(op="columns") (items[].slug, hyphenated); only kind == "input" columns are writable. The tool reads the columns first and refuses unknown / non-input slugs with the list of valid ones (the API would answer 400 UNKNOWN_FIELDS). dry_run=True runs the same validation and returns {dry_run: true, would_upsert: {rows, match_columns, enrich, keys, sample}, check} — nothing written. The real call returns the enrichment_run receipt {id, counts: {inserted, updated, skipped}}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "op": "<op>",
      "table_id": "<table_id>"
    },
    "name": "origami_rows"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYes"list" | "upsert".
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
rowsNoop="upsert" — the rows, `{slug: value}` (max 100 per call).
limitNoop="list" — rows per page (default 50, max 200).
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
cursorNoop="list" — `cursor` returned by a previous call (resume).
enrichNoop="upsert" — enrich freshly INSERTED rows (spends Origami credits). Default False (the API default is true — here you opt in).
_run_idNoOBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
dry_runNoop="upsert" — validate + preview, write nothing.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
table_idYesthe table.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
max_pagesNoop="list" — pages to follow server-side (default 1, cap 20).
match_columnsNoop="upsert" — input-column slugs used as the match key (e.g. ["email"]); every row must carry a non-empty value for each.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the whole burden and does it well: it discloses the write path, pagination mechanics (50-row pages, limit cap 200, max_pages cap 20, truncated+cursor resume), the upsert matching rule, that the tool validates slugs client-side and refuses unknown/non-input slugs instead of getting a 400, that dry_run writes nothing, that enrich spends credits and is inverted from the API default, and what the receipt looks like.

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 the one-line purpose, then split by op value so an agent can read only the branch it needs. The density is high but mostly earned; some nested parentheticals and backticked fragments make it slower to scan than it could be.

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?

A 14-parameter, annotation-free, dual-mode mutation tool with no output schema is exactly the case where a description must explain return shapes, defaults, caps and failure modes — and this one does, describing both the list envelope and the upsert receipt plus the dry_run preview payload.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: cursor is framed as a resume token tied to truncated, match_columns is explained as the update-vs-insert discriminator with a non-empty-value requirement, and enrich's inverted default is spelled out. The _org/_group/_project/_run_id/_instance scoping parameters are not discussed in the description, relying entirely on schema text.

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 first line names the resource precisely ("Rows of an Origami table") and the two operations (read vs upsert), and explicitly claims row-level write exclusivity ("the ONLY write path for rows"). This separates it cleanly from sibling origami_tables, which handles columns/schema rather than row data.

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 op breakdown gives clear conditions for each mode: list when you want to page rows, upsert when you need to write, with dry_run=True recommended implicitly by its preview semantics. It also redirects to origami_tables(op="columns") to obtain slugs, which is a prerequisite pointer rather than an alternative-tool routing. No statement of when NOT to use it (e.g. bulk CSV import via origami_upload_csv) keeps it short of a 5.

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

All Tulina toolsInspect
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