Skip to main content
Glama

Score Text

topic_scorer_score
Read-onlyIdempotent

Scores text against every category in all six taxonomies (one embedding, cosine similarity) and returns the top per rows per taxonomy. With taxonomy and category it also returns the target's rank, score, gap to #1, and a phrase bank split into phrases the text already uses and phrases it does not. Read the rank and the gap, not the raw percent (scores compress into a 70 to 90 band). Free; read-only and safe to retry.

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": "topic_scorer_score"
  }
}

Input Schema

NameRequiredDescriptionDefault
perNoRows per taxonomy.
fullNoScore the whole text as the mean of 8,192-char chunks instead of only the first 8,192 chars.
textYesThe page or draft text to score, as plain text or HTML (tags are stripped). 1 to 32768 characters. URLs are not fetched; send the content.
phrasesNoPhrase bank size for the target category (0 skips it).
categoryNoTarget category id, full path, or a unique path substring within the taxonomy (use topic_scorer_find to look one up).
taxonomyNoTaxonomy of the target category.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations cover the safety profile, yet the description still adds non-obvious operational facts: the cost (free), that one embedding is computed and compared by cosine similarity, and critically that scores compress into a 70–90 band so rank/gap are the meaningful signals. That interpretive caveat is exactly the kind of behavior an agent cannot infer from schema or annotations.

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 the primary action and return shape, followed by the conditional extension and the interpretation caveat. Dense and largely waste-free, though the parenthetical mechanism note and the trailing cost clause make it slightly longer than strictly necessary for a six-parameter tool.

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?

There is no output schema, and the description compensates by naming the returned fields (top rows, rank, score, gap, phrase bank split) and warning how to read them. What's missing is minor: no note on ordering guarantees or how the phrase bank behaves when `phrases=0`, but an agent can call it confidently.

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

Parameters4/5

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

Schema coverage is 100%, so a baseline of 3 applies, and the description earns above that by revealing behavior the schema doesn't: `per` bounds rows per taxonomy, and `taxonomy`+`category` jointly trigger extra output (rank, score, gap to #1, phrase bank split by presence). It restates little and adds real conditional semantics.

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 specific verb and resource ("scores text against every category in all six taxonomies") plus the mechanism (one embedding, cosine similarity) and the default return shape (top `per` rows per taxonomy). The conditional behavior with `taxonomy`+`category` is spelled out, so the tool is clearly distinguishable from the sibling find/gate/phrases/taxonomies tools.

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 explicit interpretive guidance — "Read the rank and the gap, not the raw percent" — and cost/retry guidance ("Free; read-only and safe to retry"), and points to `topic_scorer_find` for resolving a category. It doesn't state when to prefer `topic_scorer_gate` or `topic_scorer_phrases` instead, so the routing is implied rather than complete.

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