Skip to main content
Glama
Sign In
uleszka

uleszka

by jokerwader
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Szukaj w artykule lub książce

find_in_article
Read-only

Search a single article or library book for every occurrence of a word or phrase and return verbatim passages with context; useful for long texts, with case- and diacritic-insensitive matching.

Instructions

Finds all places in ONE article or library book where the given words occur and returns verbatim passages with context. Useful for long texts. Matching ignores case and Polish diacritics.

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": {
      "id": "<id>",
      "phrase": "<phrase>"
    },
    "name": "find_in_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesid albo tytuł artykułu (albo id książki z biblioteki)
limitNo
phraseYesSłowo lub fraza (wyszukiwane jako ciąg znaków, także fragment słowa)
contextNoIle znaków kontekstu z każdej strony

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, yet the description still adds real behavioral value: it discloses the return shape (verbatim passages with context) and the matching semantics (case- and Polish-diacritic-insensitive). It does not mention result capping, which slightly undercuts the phrase 'all places'.

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?

Three short sentences, front-loaded with the core action and return value; the matching rule follows logically. 'Useful for long texts' is the only soft sentence, but it does carry usage signal.

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?

For a four-parameter read-only tool with no output schema, the description covers purpose, return format and matching rules adequately. The gap is the unmentioned result limit, which conflicts mildly with the 'finds all places' claim.

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?

With 75% schema coverage the schema documents phrase, context and id (including id-or-title), so the baseline 3 applies. The description adds the useful semantic that matching is substring-based and diacritic-insensitive, but says nothing about the limit parameter or that 'all places' is bounded by its default of 15.

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?

The description names a specific verb (finds) and resource (occurrences within ONE article or library book) and states what is returned (verbatim passages with context). The emphasized 'ONE' implicitly separates it from whole-library search tools, though no sibling is named outright.

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

Usage Guidelines3/5

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

It gives a situational cue ('Useful for long texts') but never states when to prefer it over search or search_by_meaning, nor when not to use it. The agent must infer the single-document vs global-search split from the word 'ONE'.

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

Deploy Server

Other Tools