Agent Coach (Upskill)

Set goals and KPIs

set_goals

Idempotent

Use this after registering (and whenever goals change). Goal intake: job_type, stage, ONE north-star metric with a fixed definition and baseline, the named deliverable, capability gaps, goals, optional secondary KPIs, tools, constraints. Changing the north-star definition is recorded as drift.

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": {
      "goals": "<goals>",
      "north_star": "<north_star>"
    },
    "name": "set_goals"
  }
}

Input Schema

Name	Required	Description
`kpis`	No	Optional secondary KPIs
`role`	No	One line: what you do for your owner
`tags`	No
`goals`	Yes	Plain-language goals
`stage`	No
`tools`	No
`api_key`	No	Your Agent Coach api_key from register_agent. Optional if you send it as an Authorization: Bearer header.
`job_type`	No
`platform`	No
`job_title`	No
`north_star`	Yes	ONE declared north-star metric with a fixed definition and today's baseline
`constraints`	No	constraints: {free_only, monthly_budget_usd, owner_present, notes}
`deliverable`	No	The named deliverable you're working toward, e.g. 'first 10 paying accounts' or 'iPhone app on TestFlight'
`owner_email`	No	Add or change your owner's email (enables key recovery)
`owner_digest`	No	true: email your owner a daily digest at owner_email; false: stop it. Omit to keep the current setting (default off).
`capability_gaps`	No	Where you get stuck: auth-identity, payments-credential-separation, deploy-release, distribution, measurement, long-task-durability, quality-verification, owner-alignment

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare idempotent=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely non-obvious behavior: changing the north-star definition is recorded as drift. It does not describe what is returned or what happens to previously set goals when omitted fields are re-sent.

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?

Two sentences, usage condition front-loaded, followed by a compact field inventory; no filler. The dense list is readable but slightly compressed for 16 parameters with nested objects.

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

Completeness3/5

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

For a 16-parameter mutation with nested objects and no output schema, the description covers the main intake fields and drift behavior but says nothing about the response, whether omitted fields are cleared or preserved, or how constraints interact with recommendations. Adequate, not complete.

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?

At 63% schema coverage the description meaningfully compensates by enumerating the intake shape (job_type, stage, north-star with fixed definition and baseline, deliverable, capability gaps, goals, secondary KPIs, tools, constraints) and by stressing the ONE north-star constraint. It omits role, tags, platform, job_title, owner_email and owner_digest, so a few parameters remain schema-only.

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?

"Goal intake" plus the enumerated field list makes clear this registers an agent's goals, north-star metric, deliverable and KPIs, which is a specific verb+resource distinct from register_agent. It stops short of naming sibling tools it should not be used for, so it is not 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use this after registering (and whenever goals change)" gives explicit timing and a re-invocation condition. There is no when-not guidance or reference to an alternative tool for partial updates, which keeps it below 5.

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

All Agent Coach (Upskill) tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?