Skip to main content
Glama
Sign In

Memorables

by es.memorabl
OverviewDiscussionsAdmin

Look at works

look_at_works
Read-onlyIdempotent

See for yourself the stills of up to 4 works, to judge or compare how they look (colours, mood, composition, style). Only when the question is about appearance and the captions are not enough: it is slower. Give page addresses or slugs from a previous result.

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": {
      "works": "<works>"
    },
    "name": "look_at_works"
  }
}

Input Schema

NameRequiredDescriptionDefault
worksYes1 to 4 works: their pages (https://memorabl.es/work/...) or slugs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Read-only and idempotent behavior is already covered by annotations, but the description adds the latency warning ('it is slower') and clarifies that the return is visual stills rather than text metadata, which the annotations do not convey. It stops short of describing image format, resolution, or failure behavior for bad slugs.

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?

Two sentences, no filler: the capability comes first, the gating condition and its cost rationale come second. Every clause carries information the agent needs to make the call.

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 single-parameter, closed-world read tool with no output schema, the description covers what the tool yields (stills), the batch limit, input sourcing, and cost. Only the handling of invalid or unresolvable slugs is left unstated.

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?

Schema coverage is 100%, so the schema already documents the array, the 1–4 range, and the page-or-slug formats. The description only adds the provenance hint ('from a previous result'), which is mildly useful but not meaningfully more than the structured field.

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 uses a concrete verb and resource: fetch stills (images) of up to 4 works, so the agent can judge appearance (colours, mood, composition, style). That clearly distinguishes it from metadata-oriented siblings ('the captions are not enough'), though it never names an alternative tool, so a 4 is right rather than a 5.

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?

It gives an explicit gate ('Only when the question is about appearance and the captions are not enough') plus a cost signal ('it is slower'), which makes the trade-off against cheaper alternatives actionable. This is when-to-use, when-not-to-use, and why, in one sentence.

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

All Memorables 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