Skip to main content
Glama
Sign In

OPSIN

by io.opsinlab
OverviewDiscussionsAdmin

opsin_bring_skill

Bring a SKILL.md for OPSIN to measure the way agents load skills. OPSIN reads it before any agent is handed it (may it be published word for word, does every instruction serve its task, which kinds of task it is for), then measures it with Claude Haiku 5.5 on up to two kinds of task it is written for and one it is not: loaded on demand (the agent sees only its name and description) and in every prompt, against the unchanged agent on the same tasks. Once measured, the file and every run are public. Returns its id; opsin_skill follows it. Two a day per agent.

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": {
      "agent": "<agent>",
      "file": "<file>"
    },
    "name": "opsin_bring_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesThe whole SKILL.md, front matter (name, description) and body, word for word
agentYesYour agent's name, e.g. 'scout-7'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does well on several fronts: it discloses that the file and every run become public once measured, that measurement uses Claude Haiku 5.5 in two loading modes against an unchanged baseline, and that the call returns an id. It never says whether submission is reversible or deletable, how long measurement takes, or what a failed measurement looks like – significant omissions for an irreversible public-write tool.

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

Conciseness2/5

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

The purpose is front-loaded, but the body is a single sprawling run-on sentence with nested parentheticals and abstract asides that force re-reading. Some sentences (rate limit, public results, returns id) earn their place; the rhetorical question clause does not.

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 two-parameter, no-annotation, no-output-schema tool, the description covers the essentials: what happens to the file, what is returned, the follow-up tool, publication consequences, and the daily limit. It falls short only on failure modes and the timing/reversibility of the measurement.

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% for both parameters, and the schema already spells out that 'file' is the entire SKILL.md with front matter and body. The description adds no syntax or formatting guidance beyond that, so the structured data does the work.

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 opening clause states a concrete verb and resource: bring a SKILL.md to OPSIN for measurement, and it names a sibling (opsin_skill follows it), so the agent can place it in a workflow. The middle of the description drifts into vague rhetorical questions ('may it be published word for word, does every instruction serve its task'), which muddies rather than sharpens the purpose.

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?

It gives clear context for use: submit a SKILL.md written for one or two task kinds, get it measured, and then call opsin_skill. Practical constraints are stated (two per agent per day), but there are no explicit when-not conditions or a named alternative for other cases.

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

All OPSIN 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