Tulina

data_app

SHOW a table to the user: draws its rows INLINE in the conversation, in the app's own table look (typed cells, select colours, links). READ-ONLY.

Use it whenever the user wants to SEE or browse a table's content; then answer in text. WITHOUT datastore = the list of your tables. To read rows yourself, use data_rows — this view gives you only a one-line summary.

CHOOSE the columns: pass fields with only those that matter for the question (in the order to show them) — most tables have more columns than a reader needs. Omitted = the declared columns, in schema order. Keep limit small: the user scrolls and asks for more; the default (25) is usually right.

Sort, filter and search are arguments, same grammar as data_rows: call again to change them. Next page = the next_cursor of the previous call, with the SAME order_by/q (a cursor never crosses from one to the other).

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": "data_app"
  }
}

Input Schema

Name	Required	Description	Default
`q`	No	free-text search, as in `data_rows`.
`row`	No	show ONE record — matched against `_id`, the declared business key, or the title field value, among the rows `filter`/`q` select.
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`limit`	No	rows shown (default 25, max 200).
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`cursor`	No	`next_cursor` of the previous call, for the next page.
`fields`	No	the columns to show, in order; omit = the declared ones.
`filter`	No	`{column: value}` or `{column: {op: value}}`, as in `data_rows`.
`_run_id`	No	OBLIGATOIRE 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.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`order_by`	No	sort column (user or `_created_at`/`_updated_at`).
`datastore`	No	the table's NUMBER (`ns_id`), or `slot:<name>`; omit = list your tables.
`order_dir`	No	`desc` (default) or `asc`.	desc
`show_meta`	No	also show `_id`/`_created_at`/`_updated_at`.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it declares READ-ONLY and, crucially, discloses the non-obvious behavior that the agent itself only receives 'a one-line summary' while the rows are rendered for the user. It also explains cursor semantics and that the view is regenerated on re-call rather than mutated.

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 purpose in the first sentence, then organized under clear topical headers (use case, table selection, column choice, sorting/pagination). Dense but every block contributes; only minor redundancy in restating that sorting/filtering match `data_rows` after already deferring to it.

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, no-annotation, no-output-schema tool the description covers what an agent needs: what it returns to the caller, how to select tables and columns, paging, and the read-only contract. It leaves tenant scoping (`_org`/`_project`/`_run_id`) to the schema, which is acceptable given full schema coverage but is the remaining gap.

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; the description still adds value by stating that `fields` controls order and that omitted means declared columns in schema order, that omitting `datastore` lists tables rather than showing rows, and by stating the cursor/`order_by`/`q` coupling rule that the schema does not express. The auth/scoping parameters (`_org`, `_project`, `_run_id`) get no additional treatment beyond their schema text, which is reasonable for a read-only view.

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 and resource ('SHOW a table to the user: draws its rows INLINE in the conversation') and immediately distinguishes itself from the sibling that reads data for the agent ('To read rows yourself, use `data_rows`'). The distinction between a user-facing rendered view and an agent-facing data read is unambiguous.

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 says when to use it ('whenever the user wants to SEE or browse a table's content'), names the alternative and its role, and explains the special no-`datastore` mode as a table listing. It also gives operative guidance on limit sizing, re-calling to change sort/filter, and the pagination rule (cursor must be paired with the same `order_by`/`q`).

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

All Tulina 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?