AgentIndex

Get tool details

get_tool_detail

Read-only

Get the full AgentIndex record for one tool when you already have its id (from search_tools, get_trending or an AgentIndex URL such as agentindex.app/en/tool//). Returns name, description, long intro, summary, features, use cases, pros and cons, when to choose or skip it, compatibility, install command, license, stars, last update date, tags, rank_score, website and GitHub URL. Fields that were never filled in are omitted. Returns an isError result if no tool has that id; use search_tools to find the right id.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Tool id exactly as returned by search_tools or get_trending, usually "<github-owner>-<repo>", e.g. "hangwin-mcp-chrome".

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Tool id for get_tool_detail
`cons`	No	Weaknesses
`name`	Yes
`pros`	No	Strengths
`tags`	No
`stars`	No	GitHub stars, e.g. "12.3k"
`ai_tags`	No
`license`	No
`skip_if`	No	When to pick something else
`summary`	No	Short summary, { en, zh } or a string
`website`	No
`category`	No
`features`	No	Feature list
`choose_if`	No	When to pick this tool
`use_cases`	No	Use case list
`github_url`	No
`intro_long`	No	Longer introduction
`rank_score`	No	AgentIndex rank, 0-100
`description`	No
`last_updated`	No
`compatibility`	No	Compatible clients and platforms
`install_command`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 16, 2026

changedInput schema / properties / id / description

Previous value: -"Tool ID (e.g. \"owner-repo-name\")"New value: +"Tool id exactly as returned by search_tools or get_trending, usually \"<github-owner>-<repo>\", e.g. \"hangwin-mcp-chrome\"."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "ai_tags": {
+      "items": {
+        "type": "string"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "category": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "choose_if": {
+      "description": "When to pick this tool"
+    },
+    "compatibility": {
+      "description": "Compatible clients and platforms"
+    },
+    "cons": {
+      "description": "Weaknesses"
+    },
+    "description": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "features": {
+      "description": "Feature list"
+    },
+    "github_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "id": {
+      "description": "Tool id for get_tool_detail",
+      "type": "string"
+    },
+    "install_command": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "intro_long": {
+      "description": "Longer introduction"
+    },
+    "last_updated": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "license": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "name": {
+      "type": "string"
+    },
+    "pros": {
+      "description": "Strengths"
+    },
+    "rank_score": {
+      "description": "AgentIndex rank, 0-100",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "skip_if": {
+      "description": "When to pick something else"
+    },
+    "stars": {
+      "description": "GitHub stars, e.g. \"12.3k\"",
+      "type": [
+        "string",
+        "number",
+        "null"
+      ]
+    },
+    "summary": {
+      "description": "Short summary, { en, zh } or a string"
+    },
+    "tags": {
+      "items": {
+        "type": "string"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "use_cases": {
+      "description": "Use case list"
+    },
+    "website": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "id",
+    "name"
+  ],
+  "type": "object"
+}

First observedOct 16, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral context beyond that: unfilled fields are omitted from the response, and a missing id yields an isError result rather than an empty record. It stops short of anything about response size or latency, but the mutation/error profile is well disclosed.

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

Conciseness3/5

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

The first sentence is well front-loaded and the error-handling sentence earns its place, but the middle sentence enumerates roughly twenty returned fields that the output schema already defines — that list is the bulk of the description and is largely redundant padding.

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 single-parameter read tool with an output schema, an agent needs only the precondition, what comes back, and the failure mode — all three are present, along with the alternative to use on failure. Nothing required for a correct call is missing.

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% and the single 'id' parameter's format ('<github-owner>-<repo>', example given) lives in the schema. The description only echoes the provenance of the id ('as returned by search_tools or get_trending'), adding no syntax or validation detail, so this is the baseline case where the schema does the work.

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 precise verb+resource ('get the full AgentIndex record for one tool') and scopes it to the single-record-by-id case, which cleanly separates it from search_tools, get_trending and list_categories. An agent can pick this tool without opening the schema.

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?

Explicitly states the precondition ('when you already have its id') and names the upstream sources that supply that id (search_tools, get_trending, an AgentIndex URL). It also names the fallback ('use search_tools to find the right id') for the failure case, so both when-to-use and when-not-to-use are covered.

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

All AgentIndex tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?