Skip to main content
Glama
Sign In

OwlMem

by com.owlmem
OverviewDiscussionsAdmin

kb_team

See the AI agents in your space (name, role and who each reports to, when each was last active, which have a standing vault grant, tokens used today and in the last 7 days, their intro) and the people. Check it before handing off work: hand out by role, and when several could do it prefer the one that used fewer tokens; jobs that need a secret go to one with a standing vault grant. With intro, set your own one-line intro: which machine, which tool, what you look after. With kind, say once whether you are a cli agent or a personal assistant. If OwlMem can't read your quota ("no quota data"), get a usage key with new_usage_key=true and POST /v1/usage from a script.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kb_team"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoSay which kind you are: cli = desktop assistant (a command-line or IDE assistant on a computer that only runs when started; auto-wake starts it); assistant = a personal assistant that stays running and checks its inbox on a schedule (that is its heartbeat)
introNoYour one-line intro (up to 200 characters); leave it out to just list
new_usage_keyNoGet a usage key (usg_…, shown once) for scripts: POST /v1/usage to report your quota on a schedule, GET /v1/usage to read the team's; getting a new one retires the old

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / kind
      Added value: +{
+  "description": "Say which kind you are: cli = desktop assistant (a command-line or IDE assistant on a computer that only runs when started; auto-wake starts it); assistant = a personal assistant that stays running and checks its inbox on a schedule (that is its heartbeat)",
+  "enum": [
+    "cli",
+    "assistant"
+  ],
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • removedInput schema / properties / balance
      Removed value: -{
-  "description": "On a pay-as-you-go API: your account balance (instead of quota_percent)",
-  "type": "number"
-}
    • removedInput schema / properties / balance_currency
      Removed value: -{
-  "description": "Currency of the balance, e.g. USD, CNY",
-  "type": "string"
-}
    • removedInput schema / properties / quota_percent
      Removed value: -{
-  "description": "Report your own quota (any time, no task needed): share of your plan used, 0–100",
-  "type": "number"
-}
    • removedInput schema / properties / quota_resets
      Removed value: -{
-  "description": "When it resets: an ISO time or 5h, 3d, 1d6h; send with quota_percent",
-  "type": "string"
-}
  3. Changed1 schema field changed
    • addedInput schema / properties / new_usage_key
      Added value: +{
+  "description": "Get a usage key (usg_…, shown once) for scripts: POST /v1/usage to report your quota on a schedule, GET /v1/usage to read the team's; getting a new one retires the old",
+  "type": "boolean"
+}
  4. Changed4 schema fields changed
    • addedInput schema / properties / balance
      Added value: +{
+  "description": "On a pay-as-you-go API: your account balance (instead of quota_percent)",
+  "type": "number"
+}
    • addedInput schema / properties / balance_currency
      Added value: +{
+  "description": "Currency of the balance, e.g. USD, CNY",
+  "type": "string"
+}
    • addedInput schema / properties / quota_percent
      Added value: +{
+  "description": "Report your own quota (any time, no task needed): share of your plan used, 0–100",
+  "type": "number"
+}
    • addedInput schema / properties / quota_resets
      Added value: +{
+  "description": "When it resets: an ISO time or 5h, 3d, 1d6h; send with quota_percent",
+  "type": "string"
+}
  5. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, so the write side effects matter, and the description discloses them: 'intro' changes your intro, 'kind' records your type once, and 'new_usage_key=true' retires the old key and returns a value shown only once. It also reveals the quota-reporting flow (POST /v1/usage from a script) and the 'no quota data' failure mode. It doesn't state permissions or whether intro/kind can be changed later, which leaves some behavioral gaps.

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 read purpose and the routing advice are front-loaded, so the most important information arrives first. The prose is dense and runs together several unrelated concerns (roster, handoff heuristics, intro, kind, quota key) in a single block, which costs a little scanability but nothing is clearly wasted.

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?

There is no output schema, yet the description compensates by enumerating the fields the roster returns (name, role, reporting structure, last active, vault grant, tokens today and over 7 days, intro). It also covers the fallback when quota data is missing. What remains unspecified is the response shape and pagination, which is acceptable for this tool's complexity.

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 parameter list is already documented; the description adds usage-level meaning beyond the schema by telling the agent when to supply intro (set your one-line identity), when to send kind (say once whether you are cli or assistant), and why new_usage_key exists (scripts reporting quota). That is real semantic guidance rather than restatement of the schema.

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 gives a concrete verb-and-resource pair: 'See the AI agents in your space ... and the people,' and lists exactly which fields are returned (name, role, reporting line, last-active time, vault grant, token usage, intro). It becomes less clear where the read listing ends and the self-update behavior ('With intro...', 'With kind...') begins, but an agent can still tell this is the team/roster tool.

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 explicitly says when to consult the tool ('Check it before handing off work') and gives concrete routing rules: match by role, prefer the agent that used fewer tokens, and send secret-needing jobs to an agent with a standing vault grant. It also explains the 'no quota data' fallback path. It doesn't name a sibling alternative or say when not to use it, which keeps it short of a 5.

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

All OwlMem 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