Skip to main content
Glama

Reviews

dt_reviews
Read-onlyIdempotent

Retrieves paginated patient reviews for doctors, centers, or offers, including star ratings, text, dates, and replies so you can page through results and inspect low ratings.

Instructions

Patient reviews (doctors and centers newest first, offers oldest first): stars 1-5, text, date and reply.

No sort or filter upstream: page through to find low ratings. The summary is in dt_doctor.

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": {
      "of": "<of>",
      "id": "<id>"
    },
    "name": "dt_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesHash id or page URL, e.g. 'xqbEWZ'.
ofYesWhose reviews.
pageNo1-based page number.
limitNoReviews per page.
full_textNoReturn full texts, not cut.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.5.0
    • changedInput schema / properties / full_text / description
      Previous value: -"Return complete texts instead of cutting long ones."New value: +"Return full texts, not cut."
    • changedInput schema / properties / id / description
      Previous value: -"Hash id or page URL of the doctor, center or offer, e.g. 'xqbEWZ'."New value: +"Hash id or page URL, e.g. 'xqbEWZ'."
    • changedInput schema / properties / of / description
      Previous value: -"Whose reviews: a doctor, a center or a clinic offer."New value: +"Whose reviews."
  2. Changed8 schema fields changedv0.3.0
    • addedInput schema / properties / full_text
      Added value: +{
      +  "default": false,
      +  "description": "Return complete texts instead of cutting long ones.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / id / description
      Previous value: -"Hash id or page URL of the doctor, center or offer, e.g. 'xqbEWZ' or 'https://doctoreto.com/center/raz-shiraz-lap/YNrrOb'."New value: +"Hash id or page URL of the doctor, center or offer, e.g. 'xqbEWZ'."
    • removedInput schema / properties / id / title
      Removed value: -"Id"
    • removedInput schema / properties / limit / title
      Removed value: -"Limit"
    • removedInput schema / properties / of / title
      Removed value: -"Of"
    • removedInput schema / properties / page / title
      Removed value: -"Page"
    • removedInput schema / title
      Removed value: -"dt_reviewsArguments"
    • changedOutput schema / (root)
      Previous value: -{
      -  "additionalProperties": true,
      -  "title": "dt_reviewsDictOutput",
      -  "type": "object"
      -}New value: +null
  3. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond them: ordering differs by entity type (doctors/centers newest first, offers oldest first) and there is no server-side sort or filter, forcing pagination. It does not mention result-size limits or whether page overflow is capped, which the schema alone reveals.

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?

Two compact sentences plus a short pointer, with the most decision-relevant fact (per-entity ordering) and the constraint (no sort/filter) front-loaded. Every clause carries information; only the parenthetical phrasing is slightly compressed to the point of ambiguity.

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?

With no output schema, the description compensates by listing the returned fields and their ordering, and annotations cover the safety profile. Combined with a fully documented 5-parameter schema, an agent has enough to call it correctly; only pagination boundaries and total-count behavior are left implicit.

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 100%, so all five parameters (id, of, page, limit, full_text) are already documented, making 3 the baseline. The description adds only indirect meaning — that 'of' accepts doctors, centers and offers, and that ordering varies by that value. It says nothing additional about page/limit/full_text behavior.

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?

The description names the resource (patient reviews) and enumerates the returned fields (stars 1-5, text, date, reply) with per-entity ordering rules, so an agent knows exactly what it gets. It does not state an explicit verb like 'fetch/list', and the parenthetical mixes entities, but it clearly differentiates itself from dt_doctor by pointing there for the aggregate summary.

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?

"No sort or filter upstream: page through to find low ratings" gives concrete operating guidance for a review-listing tool that lacks filter parameters. "The summary is in dt_doctor" redirects to the appropriate sibling for aggregate data. It stops short of naming when to prefer dt_search_doctors or other siblings, so there is no full when-not guidance.

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