Skip to main content
Glama

hooks_score

Idempotent

Score one hook (the opening line of a post or video) from 0 to 100. Free (no credits). Returns the pattern it uses, its strengths, concrete fixes, the score breakdown and an estimated percentile with the basis it was estimated on (say "estimated" when you quote it). "rewrite" is a stronger version that was scored too ("rewriteScore") and beats the hook without being longer; when there is none, no version we wrote scored higher: say the hook already holds up and give the fixes, never invent a rewrite. Use it when the user asks "is this hook good?", or to check a hook before generating content with it. Works without a brand profile, but is sharper with one.

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": {
      "text": "<text>"
    },
    "name": "hooks_score"
  }
}

Input Schema

NameRequiredDescriptionDefault
saveNoAlso save the hook to the hook history (default false: score only). Set true when the user wants to keep it
textYesThe hook, word for word
platformNoWhere it will be posted (default tiktok)
audienceIdNoAn audience id from brand_profile

Output Schema

NameRequiredDescriptionDefault
idNoSaved hook id, only when save was true
textNo
errorNo
fixesNo
scoreNo
patternNo
rewriteNo
benchmarkNo
breakdownNo
strengthsNo
rewriteScoreNoThe rewrite's own score, higher than the hook's

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / rewriteScore
      Added value: +{
      +  "description": "The rewrite's own score, higher than the hook's",
      +  "type": "number"
      +}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: it lists the returned artifacts (pattern, strengths, fixes, score breakdown, percentile), imposes a disclosure rule on the percentile ("say 'estimated'"), and forbids inventing a rewrite when none scored higher. That said, the annotations' readOnlyHint=false is never explained — the description doesn't note that the tool can persist data when save is set — leaving a small gap between the non-read-only annotation and the "score only" framing.

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-loads purpose and cost, then layers the return shape, then the usage trigger. Several sentences are guardrail directives to the caller (quote "estimated", never invent a rewrite) that are valuable but make it longer than a minimal definition; the uneven indentation and quoted-field naming slightly reduce scannability.

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?

With an output schema and annotations already covering safety, the description fills the remaining gaps an agent needs: what the score result contains, how to report the percentile honestly, how to handle the absence of a rewrite, cost, and the optional brand-profile dependency.

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 text, platform, save and audienceId are already documented in the schema. The description only indirectly touches audienceId via "works without a brand profile," adding no syntax or format meaning beyond the structured fields; baseline 3 applies.

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?

Names a specific verb and resource ("Score one hook (the opening line of a post or video)"), states the output scale (0 to 100) and the cost (free), which lets an agent distinguish scoring from the sibling generation tool referenced by "before generating content with it."

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 triggers ("when the user asks 'is this hook good?'" or pre-generation checks) and a prerequisite note ("works without a brand profile, but is sharper with one"). It never names hooks_generate or another sibling as the explicit alternative, so routing is implied rather than spelled out.

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