Skip to main content
Glama

Goodeye

by dev.goodeye
OverviewDiscussionsAdmin

optimize_description

Read-only

Tune an existing skill's trigger: sharpen its description so it fires at the right times.

Pack-returner: response is {skill_md, references, skill_id, max_iterations}. The agent runs the loop locally with the user to tune the skill's description (the text that decides when the skill fires) for trigger accuracy, then persists the winner via save_skill(source='description_optimization') only after explicit user approval. Only the description changes; body, outcome, tags, and sibling files carry forward unchanged. Requires edit access on the skill.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skill_idYesThe skill to act on, identified by its UUID, slug, or name.
max_iterationsNoOptimization loop budget (1 to 1000). Defaults to 10 when omitted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / skill_id
      Added value: +{
+  "description": "The skill to act on, identified by its UUID, slug, or name.",
+  "type": "string"
+}
    • removedInput schema / properties / workflow_id
      Removed value: -{
-  "description": "The workflow to act on, identified by its UUID, slug, or name.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "workflow_id"
-]New value: +[
+  "skill_id"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

The description discloses that only the description changes, while body, outcome, tags, and sibling files carry forward unchanged. It also states the requirement for edit access and explicit user approval before persisting. The annotations declare readOnlyHint=true, which aligns with the description's emphasis on local tuning and approval-gated persistence. The description adds meaningful behavioral context beyond the annotations.

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?

The description is compact and front-loaded with the core purpose. Every sentence adds value: the purpose, the workflow, the scope of changes, and the access requirement. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a tool with 2 parameters, full schema coverage, and an output schema. It explains the workflow, the constraints, the approval requirement, and the persistence path. An agent has enough context to select and invoke the tool correctly without needing additional details.

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 schema already documents both parameters. The description adds context by explaining the optimization loop budget ('max_iterations') and the persistence condition, which helps the agent understand the parameter's role in the workflow. It doesn't add syntax details, but the schema already covers those.

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?

The description states a specific verb ('Tune'), a specific resource ('an existing skill's trigger'), and the exact mechanism ('sharpen its description so it fires at the right times'). It also distinguishes itself from the sibling 'optimize_skill' by focusing on description/trigger accuracy rather than general optimization.

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?

The description explicitly says when to use this tool: to tune a skill's description for trigger accuracy. It also names the persistence path ('save_skill(source='description_optimization')') and the requirement of explicit user approval, which clarifies the workflow and when it should be invoked.

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

All Goodeye 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