Tulina

granola_content

Meeting content — notes, transcripts, and folders.

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": "granola_content"
  }
}

Input Schema

Name	Required	Description	Default
`op`	No	"list_notes" (default) \| "get_note" \| "get_transcript" \| "list_folders".	list_notes
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`cursor`	No	pagination cursor from a previous response — valid on "list_notes"/"get_transcript"/"list_folders".
`_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.
`include`	No	op="get_note" only — "transcript" inlines the transcript in the response; may return `TRANSCRIPT_TOO_LARGE` for long meetings, use op="get_transcript" then (paginated from the start).
`note_id`	No	REQUIRED by "get_note"/"get_transcript" — the note id (`not_...`). Refused on "list_notes"/"list_folders", which enumerate everything reachable and would ignore it.
`_account`	No	Compte à OPÉRER parmi : `Alessandro` (org), `principal` (org, défaut). `oto_identity(op='list')`.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`folder_id`	No	op="list_notes" — restrict to this folder and its subfolders (from op="list_folders").
`page_size`	No	"list_notes"/"list_folders" — 1-30, default 10. "get_transcript" — 1-100, default 50.
`created_after`	No
`updated_after`	No
`created_before`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

D1.7/5.0

Behavior1/5

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

No annotations are provided, so the description carries the full burden of disclosure and it says nothing about behavior: no read-only indication, no auth/permission requirements, no pagination semantics, no mention of the TRANSCRIPT_TOO_LARGE failure mode documented in the schema. The single fragment gives the agent no behavioral context for a 4-operation tool.

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

Conciseness2/5

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

Brevity here is under-specification rather than conciseness: a single noun-phrase fragment with no front-loaded statement of purpose, no operation summary, and no structure to help an agent scan. Nothing is wasted because almost nothing is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, four-operation tool with no annotations, the description is completely inadequate — it explains neither the operation dispatch nor any prerequisite that the schema does not already encode. Only the output schema mitigates the gap by defining return shapes.

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 80% and the schema already documents per-op parameter applicability, page-size ranges, the note_id requirement, and the transcript inlining fallback, so the baseline of 3 applies. The description adds no parameter meaning of its own beyond loosely naming the content types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource domain (meeting content: notes, transcripts, folders) but supplies no verb and no indication of what the tool actually does with that content. It essentially restates the tool name 'granola_content' plus an enumeration of content kinds, and never mentions the four-way `op` dispatch that defines the tool's real purpose.

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

Usage Guidelines1/5

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

There is no when-to-use guidance at all — no mention of when to pick list_notes versus get_note versus get_transcript versus list_folders, and no reference to the only related sibling (granola_webhook_endpoint) to disambiguate. An agent must read the schema enum to discover the available operations.

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?