Skip to main content
Glama

Find words by pattern

find_words
Read-only

Searches all lists for words matching a letter pattern, for example starts_with 'sh', ends_with 'ck' or contains 'ight'. Patterns are plain case-insensitive substrings (no wildcards) and all given patterns and filters must match (AND). Returns { totalMatches, returned, matches }, each match a word with its language and every list it appears in (id, grade range, page URL), in dataset order and cut at limit (no paging). Use this to search by spelling pattern; use get_words_for_grade for a whole grade's words, or get_word_list for one known list. Calling it with none of contains, starts_with or ends_with returns an error.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_words"
  }
}

Input Schema

NameRequiredDescriptionDefault
gradeNoOnly English lists whose grade range includes this grade; other languages have no grade, so combining it with a non-en language returns no matches.
limitNoMaximum matches to return, 1 to 500. Default 60; totalMatches gives the full count.
containsNoWord contains this substring anywhere, e.g. ai or ight. 1 to 12 characters.
languageNoOnly lists in this language: en, de, es, fr, nl or pt-br. Omit to search every language.
ends_withNoWord ends with this substring, e.g. ck. 1 to 12 characters.
starts_withNoWord begins with this substring, e.g. sh. 1 to 12 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / contains / description
      Added value: +"Word contains this substring anywhere, e.g. ai or ight. 1 to 12 characters."
    • addedInput schema / properties / ends_with / description
      Added value: +"Word ends with this substring, e.g. ck. 1 to 12 characters."
    • changedInput schema / properties / grade / description
      Previous value: -"Only English lists covering this grade."New value: +"Only English lists whose grade range includes this grade; other languages have no grade, so combining it with a non-en language returns no matches."
    • addedInput schema / properties / language / description
      Added value: +"Only lists in this language: en, de, es, fr, nl or pt-br. Omit to search every language."
    • changedInput schema / properties / limit / description
      Previous value: -"Default 60."New value: +"Maximum matches to return, 1 to 500. Default 60; totalMatches gives the full count."
    • addedInput schema / properties / starts_with / description
      Added value: +"Word begins with this substring, e.g. sh. 1 to 12 characters."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses that patterns are plain case-insensitive substrings with no wildcards, that all patterns and filters combine with AND, and that the result is in dataset order and truncated at limit with no paging. It also names the non-obvious error path for an empty pattern set.

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

Conciseness5/5

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

Four tight sentences, front-loaded with purpose, then matching semantics, then return shape, then routing and the error case. No filler, no repetition of schema fields, and each sentence carries information an agent needs.

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 six-parameter search tool with no output schema, the description supplies the full result shape ({ totalMatches, returned, matches } with per-match language and list metadata), ordering, truncation, and the error condition. Nothing material is left for the agent to infer.

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 the baseline is 3, but the description still adds meaning the schema does not carry: case-insensitive matching semantics and the AND relationship across contains/starts_with/ends_with and filters. It does not restate per-parameter ranges, which is appropriate since the schema already does that.

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?

The description opens with a specific verb and resource ("Searches all lists for words matching a letter pattern") and immediately grounds it with concrete examples (starts_with 'sh', ends_with 'ck', contains 'ight'). It clearly separates this tool from get_words_for_grade and get_word_list, so an agent can pick it without opening any 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?

Explicit routing guidance is given: "Use this to search by spelling pattern; use get_words_for_grade for a whole grade's words, or get_word_list for one known list." It also states the failure condition — calling with none of contains, starts_with or ends_with returns an error — which prevents a whole class of invalid invocations.

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.