Tulina

minari_analytics

Aggregated calling metrics — answer "what's our connect rate" with one call instead of downloading and summing calls yourself.

DEFAULT WINDOWS DIFFER, and getting this wrong silently returns the wrong period: "overview" and "users" default to TODAY; "objections" defaults to the LAST 7 DAYS. Always pass start_date and end_date together when you mean a specific range. Analytics are day-granular, and the resolved window comes back in period next to the data.

Rates are percentages (0-100) and are null when their denominator is 0. The per-user rows sum to the overview totals for the same filters.

"lists" is the all-sources view of list progress (CSV, HubSpot, …) — use it, not minari_list, to answer "which lists are stalled".

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": "minari_analytics"
  }
}

Input Schema

Name	Required	Description	Default
`op`	No	"overview" is the company total; "users" breaks the same metrics down per rep (rank by connect rate); "objections" is what prospects push back on and how well reps handle it; "lists" is per-list completion and health.	overview
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`cursor`	No	"lists" only — `next_cursor` from a previous response. Re-send `period`, `call_limit` and any filters with it — the cursor is a position, not a saved query. Pages are 10, not 50.
`period`	No	REQUIRED by "lists" — the dial window counted: "day", "week", "month" or "all".
`_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.
`list_id`	No	restrict to calls made within these list id(s).
`user_id`	No	restrict to team member id(s), from `minari_user`.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`end_date`	No	"overview", "users" and "objections" only — ISO 8601, sent together with `start_date`.
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`call_limit`	No	REQUIRED by "lists" — 1 to 10, the attempts after which an unconnected contact counts as completed. With `period` it DEFINES what "completed" means, so two different values are two different questions, not a contradiction.
`start_date`	No	"overview", "users" and "objections" only — ISO 8601, sent together with `end_date`. "lists" has NO date window; its window is `period`.
`conversation_threshold`	No	"overview" and "users" only — seconds a connected call must last to count as a conversation. One of 0, 30, 60, 90, 120 (default 30).

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does well: it warns that getting the default window wrong silently returns the wrong period, notes analytics are day-granular, and states the resolved window comes back in `period`. It also explains that rates are 0-100 percentages and null on zero denominators, and that per-user rows sum to overview totals. It does not mention permissions, scoping tokens, or that the call is read-only, leaving a small gap.

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 highest-risk pitfall (differing default windows) and organized into short, scannable paragraphs. The opening framing sentence ("with one call instead of downloading and summing calls yourself") is slightly verbose, but the emphasis conventions make the important constraints easy to extract.

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 tool with an output schema and no annotations, the description covers the main traps: op-specific defaults, date pairing, day granularity, rate nullability, and lists pagination semantics. It omits any discussion of the scoping parameters (`_project`, `_org`, `_group`, `_run_id`) and safety profile, but the output schema and per-parameter descriptions carry return values and token sourcing.

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 nonetheless adds meaning beyond the schema by tying parameters to operations and warning about the silent wrong-period failure when dates are passed singly. It also clarifies that `call_limit` redefines "completed" so different values are different questions, which is genuinely useful interpretive context.

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 (aggregated metrics) and resource (calling analytics), with a concrete example question ("what's our connect rate"). It explicitly distinguishes itself from siblings, naming `minari_list` as the wrong tool for list-stall questions and framing itself as the alternative to downloading raw calls.

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?

Gives explicit per-operation guidance: the default windows differ (overview/users = today, objections = last 7 days), you must pass `start_date` and `end_date` together, and `lists` uses `period` instead of a date window. It also routes the agent to the right sibling, telling it to use this rather than `minari_list` for stalled lists.

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?