Skip to main content
Glama
Sign In

Ilu Rennik

by com.ilurennik
OverviewDiscussionsAdmin

Search your Ilu

find
Read-onlyIdempotent

Look up one fact: a policy number, renewal date, doctor, account, ID expiry. Use this when a question or task needs one thing about their life, such as their car insurance, a passport expiry, an address, a membership number or who acts for them, before booking, paying, renewing or filling a form, and to locate a policy or statement before reading it. Do not use for questions about the world at large, or for what a document says inside; that is open with look_for. One ranked search over everything the person keeps here: their facts and the files they uploaded. Ranked by words and meaning together. Filters for a company or place every match holds (about), person, date range, kind, file type and newest first. Returns ids, dates, a short snippet and the true total of word matches per kind (an item found by meaning alone says matched: meaning), paged with cursor. A snippet points to the item; open reads it. Nothing found says so, and names the document that would settle it.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
partNoWhich part of a long answer to read: the answer's `next_part`. Leave it out for the first.
aboutNoWords every match must hold: the place, company or thing they named ("Jalisco", "Banorte").
kindsNoDefault fact, document.
limitNoDefault 20, max 100.
queryNoTheir words for what to find.
cursorNonext_cursor from the last call.
personNoA person named on the fact or the file.
date_toNoLast day, inclusive.
queriesNoOther wordings, searched together (other languages, synonyms).
date_fromNoFirst day, YYYY-MM-DD, 'today' or 'yesterday'.
file_typeNopdf, image, spreadsheet, word, presentation, or an extension.
newest_firstNoMatches in date order, newest first. Set by itself when the query says last, latest or most recent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations: it discloses the ranking model (words and meaning combined), the conjunctive nature of `about`, the return shape (ids, dates, snippet, true total of word matches per kind), the `matched: meaning` marker for semantic-only hits, cursor paging, and the empty-result behavior of naming the document that would settle the question.

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?

The usage constraint and the `open` alternative are front-loaded, and almost every sentence carries distinct information. Some sentences are long and stacked ('Returns ids, dates, a short snippet and the true total...'), which costs a little readability but not enough to justify trimming substance.

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 12-parameter, no-output-schema search tool, the description covers ranking, filtering, return fields, paging, and the empty case thoroughly. The only unresolved element is how a long answer is split between `cursor` paging and the `part`/`next_part` parameter, which the description leaves to the schema.

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; the description still adds meaning by characterizing `about` as a filter every match must hold and by explaining `newest_first` as being set alone when the query says last/latest/most recent. It does not reconcile the `cursor` paging narrative with the `part`/`next_part` parameter, which is the one gap.

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?

Description opens with a specific verb and object ('Look up one fact') and enumerates concrete fact types (policy number, renewal date, doctor, ID expiry). It explicitly distinguishes itself from the sibling `open` and from world-knowledge queries, so an agent can route without opening the 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?

Gives an explicit when-to-use scenario ('before booking, paying, renewing or filling a form, and to locate a policy or statement before reading it') and an explicit when-not ('Do not use for questions about the world at large, or for what a document says inside; that is `open` with `look_for`'), naming the alternative tool and the condition that selects it.

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

All Ilu Rennik toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources