Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

serper_reviews

Read-only

Google reviews of a place.

⚠️ The default returns ALL the reviews, and that is intended. A single page (~10 reviews, sorted mostRelevant) silently under-represents a place that can have thousands: a sentiment analysis done on it is biased without anything signalling it. The default path is therefore the complete path; the sample must be requested explicitly.

op:

  • "all" (default): follows the nextPageToken cursor server-side until exhausted, or until the max_reviews cap (bounds the cost; truncated=True signals the cut). Returns {count, reviews[], pages_fetched, credits_used, truncated} — credits_used = what Serper actually deducted across all the pages, the exact cost of the call. This is what you need for global sentiment, recurring themes, a reputation.

  • "page": ONE page (~10 reviews) — quick sample, or manual pagination via next_page_token. Conclude nothing global from it.

Identify the place by cid / fid / place_id (from a serper_search(kind="places") or a serper_maps_sample) or by free query.

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": "serper_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNo"all" (default) | "page".all
cidNoGoogle customer id of the place.
fidNoGoogle feature id of the place.
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
queryNofree-text place lookup (alternative to ids).
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
_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.
countryNocountry code (default "fr").fr
sort_byNo'mostRelevant' | 'newest' | 'highestRating' | 'lowestRating'.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
languageNolanguage code (default "fr").fr
place_idNoGoogle place id.
topic_idNofilters the reviews by topic.
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
max_reviewsNoop="all" — cap on reviews fetched (default 200).
next_page_tokenNoop="page" — cursor from a previous response.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare `readOnlyHint: true`, which the description never contradicts, and the description adds substantial context beyond it: the default exhausts the `nextPageToken` cursor server-side, `max_reviews` caps cost with a `truncated=True` signal, `credits_used` reflects Serper's actual per-page deduction, and the return shape `{count, reviews[], pages_fetched, credits_used, truncated}` is spelled out. The warning that a single page "silently under-represents" a place is exactly the kind of behavioral risk an agent cannot infer from structured fields.

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 core purpose, then a bolded warning, then a bulleted breakdown of `op` — good structure for scanning. It is on the verbose side and restates the same point twice ("The default path is therefore the complete path; the sample must be requested explicitly"), which slightly dilutes an otherwise tight definition.

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?

For a 16-parameter tool with no output schema, the description supplies the return structure, the cost model, the truncation signal, the pagination contract, and the identifier-sourcing paths — everything needed to call it correctly and to interpret the result. Nothing decision-relevant is missing.

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 already 100%, so the baseline is 3, but the description goes further: it explains the semantics of `op`, ties `max_reviews` to cost-bounding and the `truncated` flag, ties `next_page_token` to the `page` mode, and states that `cid`/`fid`/`place_id` come from search/maps tools with `query` as a free-text alternative. Parameters like `topic_id`, `sort_by`, `country`, and the `_org`/`_run_id` plumbing params are left to the schema, so not a 5.

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

Purpose4/5

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

Opens with a concrete verb+resource ("Google reviews of a place") and then splits the behavior into the two `op` modes, so an agent immediately knows what it gets back. It does not differentiate itself from the sibling `apify_google_maps_reviews`, which appears to fetch the same class of data, so a 4 rather than a 5.

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?

Explicitly states when to use `op="all"` (global sentiment, recurring themes, reputation) versus `op="page"` (quick sample, manual pagination) and warns "Conclude nothing global from it." It also names where the place identifiers come from (`serper_search(kind="places")`, `serper_maps_sample`). The only gap is no guidance on choosing between this tool and the sibling `apify_google_maps_reviews`.

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