within

Guides and answers from within

find_notes

Read-onlyIdempotent

Answers designer-fashion how, which, or worth-it questions by returning up to five relevant within journal notes and edits, each with a title, one-line summary, and shopwithin.co link.

Instructions

within's own guides for a question: journal notes (how a designer's sizes run, where to shop in a city, what to wear to an occasion, how to tell real from fake) and edits (items picked around one idea). Give the question in plain words; up to five come back, each with its title, one line and its shopwithin.co link. Use this when someone asks a how, which or is-it-worth-it question about designer fashion.

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": {
      "query": "<query>"
    },
    "name": "find_notes"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes	The question in plain words: 'how do Margiela tabis run', 'Ossington shops', 'winter wedding coat'.

Output Schema

Name	Required	Description	Default
`notes`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 11, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, lowering the burden. The description adds genuine behavioral context by capping results ('up to five come back') and describing each hit's shape (title, one line, shopwithin.co link). However, the 'up to five' ceiling conflicts with the schema's limit maximum of 8, and nothing explains ranking or what happens when no note matches.

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 sentences, each carrying real information: content types, input phrasing plus return shape, and the usage trigger. The opening fragment ('within's own guides for a question:') is slightly awkward and could front-load the trigger condition sooner, but there is no filler.

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 read-only, non-destructive lookup with one required parameter, the definition covers what the tool returns, how to phrase the input, and when to reach for it, which is close to sufficient; the output schema further reduces the need to spell out results. The remaining gap is the unaddressed limit parameter and the five-versus-eight cap ambiguity.

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?

Query semantics are reinforced ('Give the question in plain words') and the schema's own description already supplies examples, so the crucial parameter is well served. The second parameter, limit, is never mentioned in the description and its absence is made more confusing by the claim that 'up to five come back' while the schema permits 1-8. With 50% schema coverage, this leaves one parameter semantically unaddressed.

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 and resource ('find within's own guides') and enumerates the two content types it covers, journal notes (size guidance, city shopping, occasion dressing, authenticity) and edits (items around one idea). That makes the resource concrete. It stops short of distinguishing itself from a plausibly similar sibling such as designer_guide or outfit_ideas, so an agent must still infer the boundary.

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?

'Use this when someone asks a how, which or is-it-worth-it question about designer fashion' is an explicit and usable trigger condition tied to question shape. There is no when-not guidance and no alternative tool is named, so routing to or away from lookalike siblings is left to inference.

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