Skip to main content
Glama

Market Brew

Semantic Focus Analyzer

analyze_semantic_focus

Use this when the user asks to run Semantic Focus Analyzer. Returns structured analysis and supported comparisons or draft previews for an API-key-enabled account. May invoke providers, consume quota and populate caches. Does not publish content or add opportunities to Launchpad. Request generation only when explicitly desired.

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": {
      "body": "<body>"
    },
    "name": "analyze_semantic_focus"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.2/5.0
Behavior3/5

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

The description adds real context beyond the annotations: it warns that the call may invoke providers, consume quota, and populate caches, and it clarifies that it is not a publishing/Launchpad action. That complements the openWorldHint=true and destructiveHint=false flags well. It still omits the API-key prerequisite details beyond a passing mention and says nothing about latency, cost magnitude, or what the returned analysis contains.

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 description is short and front-loaded, but the opening sentence carries no information and the remaining sentences are a loosely ordered mix of output, cost, and scope notes. It is efficient in length but not in information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a large nested input schema, no output schema, and zero parameter documentation, the description does far too little: it never explains what a semantic focus analysis returns or how the focus/anchors/entities inputs shape it. The quota/cache warning is a genuine plus, but the definition is not complete enough to invoke this tool confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single body parameter expands into a deeply nested schema (~25 properties including focus.anchors, focus.entities, comparisonUrl, generatePrompts, compressionLevel) with 0% description coverage, and the description explains none of it. Only the phrase "request generation only when explicitly desired" faintly maps to generatePrompts; everything else is left for the agent to guess.

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

Purpose2/5

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

The first sentence, "Use this when the user asks to run Semantic Focus Analyzer," simply restates the tool name and title without saying what a semantic focus analysis actually is. The second sentence ("Returns structured analysis and supported comparisons or draft previews") gestures at output but stays generic and never distinguishes this from siblings such as analyze_spotlight_focus or analyze_query_coverage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The stated trigger is circular: use it when the user asks for it. There is a useful conditional ("Request generation only when explicitly desired") and a scope exclusion (does not publish or add to Launchpad), but neither tells the agent when to pick this analyzer over the many other analyze_* tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources