Skip to main content
Glama

search_inspo

Search a local visual reference archive by exact words, meaning, or image similarity across filenames, folders, saved page metadata, and image labels; returns metadata only for later viewing.

Instructions

Search the person's local visual reference archive by text.

Matches across the filename and folder, a saved page's title, URL and note, and the _manifest.md label and note written for an image. Every space-separated term must match, so "cosmos paywall" narrows rather than widens.

Returns metadata only — use view_inspo afterwards to actually look at the results. Prefer searching before viewing: viewing is expensive and this is cheap.

Searches three ways at once, exactly as the app's own search box does, and says which is which: an exact match on the words; then anything the phrase reaches BY MEANING; then, if the person has switched it on, anything that looks right BY PICTURE — which is the only one that reaches an image nobody has ever described.

Supports the app's full search language: "quoted phrases" hold words together, and -negation leaves things out. Words match whole, so "red" does not match "centered".

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": "search_inspo"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoRestrict by media type.any
limitNoMaximum results.
queryYesWords to look for. Space-separated terms are ANDed together.
folderNoRestrict to one folder, e.g. "riso" or "apps". Qualify it as "@<root>/<folder>" to mean one root's copy of a folder name; unqualified matches that folder in every root. Use list_folders to see them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does substantial work: it discloses that only metadata is returned, that three recall modes run simultaneously (exact, semantic, and visual) and that the response labels which is which, and that visual matching only fires when a user setting is enabled. Gaps remain around result ordering and any cost or scope limits of the semantic/picture passes, but the disclosure is well beyond the schema.

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 opening line and the match-scope sentence are front-loaded, and the search-syntax sentence sits at the end where it belongs. The middle paragraph on the three simultaneous search modes is slightly discursive ('searches three ways at once, exactly as the app's own search box does'), but it delivers information an agent cannot get elsewhere, so it is not waste.

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?

Given four parameters, 100% schema coverage, no annotations and no output schema, the description supplies what the structured fields cannot: return-shape expectations ('metadata only'), the meaning of the search syntax, and where to go next for pixel-level inspection. It stops short of describing result ordering or what a metadata record contains, which would help an agent parse output.

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 description coverage is 100%, so a 3 is the baseline; the description earns above that by adding query semantics the schema only hints at — space-separated terms are ANDed ('cosmos paywall narrows rather than widens'), quoted phrases bind words, leading '-' negates, and matching is whole-word so 'red' excludes 'centered'. Folder and kind/limit remain schema-only, but the query language is meaningfully elaborated.

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 ('Search the person's local visual reference archive by text') and immediately enumerates the fields searched (filename, folder, page title/URL/note, _manifest.md label and note). It also distinguishes itself from the sibling view_inspo by framing search as the cheap lookup step and viewing as what happens afterwards.

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 explicit sequencing guidance: 'Prefer searching before viewing: viewing is expensive and this is cheap,' and 'use view_inspo afterwards to actually look at the results.' It also explains when the picture-based recall path applies (only if the person has switched it on), so an agent knows what results it may or may not get.

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