Skip to main content
Glama

uplika

by com.uplika
OverviewDiscussionsAdmin

Measure and judge Naver keywords into sets

research_naver_keywords
Read-only

Naver Blog only. Measures keywords (monthly searches from Search Ad, blog document count and posts per month from API HUB), judges each one (best, possible, hard, wall, hot, saturated, phantom and so on, with why), and groups them into sets for one post: a main keyword plus two to five subs with the same search intent. Every set carries prompt, a ready-to-paste Korean brief for writing the skeleton of that post. Up to 60 keywords. Measurements are cached seven days across users; new ones run against a time budget, so partial: true with unmeasured[] means the budget ran out and calling again with the same keywords finishes the rest from cache. Each call is saved as a report (reportId) unless the same keyword set was saved in the last ten minutes, which returns that report's id instead. Every set also carries draftPrompt, a brief for writing the whole post (title, subheadings, body, and bracketed photo placeholders for the person to fill); pass topic to put the post's subject in it. Returns 403 research_tool_disabled with enableUrl if the person has not turned this tool on for connectors. Tell them once and do not call it again until they say it is on.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNoWhat the post is about, one line. Goes into draftPrompt; without it the prompt tells the writer to pick a subject that fits the main keyword.
keywordsYes1-60 keywords, as the person would search them.
seedTextNoWhat the person asked for, kept as the report's label. Defaults to the first five keywords.
workspaceIdNoWhich workspace this is for. Only needed when the account has more than one — the error tells you the ids when it matters. Leave it out if it is already decided; do not ask the person again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / properties / photos
      Removed value: -{
-  "description": "One line per photo saying what it shows, in order. draftPrompt places them; a placeholder otherwise.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
    • changedInput schema / properties / topic / description
      Previous value: -"What the post is about, one line. Goes into draftPrompt; a placeholder otherwise."New value: +"What the post is about, one line. Goes into draftPrompt; without it the prompt tells the writer to pick a subject that fits the main keyword."
  2. Changed2 schema fields changed
    • addedInput schema / properties / photos
      Added value: +{
+  "description": "One line per photo saying what it shows, in order. draftPrompt places them; a placeholder otherwise.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / topic
      Added value: +{
+  "description": "What the post is about, one line. Goes into draftPrompt; a placeholder otherwise.",
+  "type": "string"
+}
  3. Added

TDQS

A4.1/5.0
Behavior5/5

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

Rich disclosure well beyond the annotations: seven-day cross-user caching, a time budget that yields partial:true with unmeasured[], a ten-minute dedupe window that returns an existing reportId, the 403 research_tool_disabled error with enableUrl, and the fact that each call persists a report. The description discloses side effects (report saving, cache writes) that readOnlyHint=true does not surface, but it does not assert the opposite of the annotation, so this is understatement rather than contradiction.

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 scope, function, and card outputs before the mechanics, and nearly every sentence carries operative detail (caching, budget, dedupe, 403 handling). It is a dense single block, however, and the prompt/draftPrompt/prompt-distinction sentences run together, making it harder to scan than it needs to be.

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?

Even with no output schema, the description explains what comes back (verdicts with reasons, sets with same-intent subs, prompt, draftPrompt), how partial results are signaled, and how failures and dedupe resolve. For a four-parameter tool with a time-budgeted, cached, error-prone backend, an agent has everything needed to call it correctly.

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 the schema already documents topic, seedText, workspaceId, and keywords in detail. The description reinforces a few things the schema says (topic flows into draftPrompt, workspaceId should not be re-asked) and adds the 1-60 keyword bound, but adds no formats or constraints beyond that. Baseline 3 applies when the schema does the heavy lifting.

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?

States specific verbs and resources: it measures Naver Blog keywords across three metrics, judges each into named verdicts (best, possible, hard, wall, hot, saturated, phantom), and groups them into post sets with main + sub keywords. The scope 'Naver Blog only' is clear. It never names or contrasts with the nearby expand_naver_keywords, get_naver_keyword_history, or list_naver_keyword_reports siblings, so differentiation is left to inference.

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?

Gives concrete usage context: Naver Blog only, up to 60 keywords, and explicit instructions for the 403 research_tool_disabled path (tell the person once, do not retry until enabled). The partial:true / unmeasured[] re-call guidance tells the agent exactly when to call again. It stops short of comparing against alternative keyword tools (expand_naver_keywords), so 'when not to use this' is only partially covered.

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

All uplika 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