Skip to main content
Glama

Tommos

by ai.tommos
OverviewDiscussionsAdmin

Read how Tommo learns

read_how_tommo_learns
Read-onlyIdempotent

How a tommo learns from people's decisions. syntheses: for each act and letter purpose (and each door of «Is this a lead?»), the open and closed reasons people gave, each with how many decisions gave it, the last one's date, who closed it and when, and its evidence — the decisions in the people's own words, each with contactName and cardTitle. failed: the decisions of this tommo that could not be read, with the reason (failure) and the same in a person's words (failureInWords). weeks: week by week (the Monday it starts on), by tommo, act and letter purpose, the cards decided, refused and edited, their share, and repeatsAKnownReason — decisions that repeat a reason already in the synthesis; repeatsCounted is false for a week before repeatsCountedSince, the first decision the learning queue kept, so its zero means not counted. tommo: one tommo's slug (from list_tommos), else the whole workspace; weeks: how many weeks back, 12 by default.

Input Schema

NameRequiredDescriptionDefault
tommoNoThe tommo's slug
weeksNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / tommo
      Added value: +{
+  "description": "The tommo's slug",
+  "type": "string"
+}
  2. First observed

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered and the description does not contradict it. The description does add one useful behavioral detail (weeks defaults to 12) and clarifies the tommo scoping, but discloses nothing about auth, pagination, or limits.

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 description is a single dense run-on paragraph that buries the tool's purpose under an enumeration of return fields. It is not front-loaded — the reader gets output-schema detail before any usable framing of what the tool is for, and the semicolon-chained clauses are hard to parse.

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?

With no output schema, the description does the heavy lifting on return values (syntheses, failed, weeks) and explains both parameters, which is genuinely useful. However, it provides no guidance on when to choose this tool over sibling reporting tools, and omits any auth or scope preconditions.

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 50% (only tommo is documented in the schema). The description compensates well: it defines tommo as a slug 'from list_tommos' with the whole workspace as fallback, and defines weeks as how many weeks back with a stated default of 12 — meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line, 'How a tommo learns from people's decisions,' names a topic rather than stating a clear verb+resource purpose. The subsequent enumeration of return buckets (syntheses, failed, weeks) implies this is a reporting tool over a tommo's learning data, but the agent must infer that from output fields. It is distinguishable from siblings only indirectly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance, despite siblings like read_the_lost_reasons and leads_report covering adjacent reporting territory. The only usage-adjacent text is the trailing parameter explanation for tommo and weeks, which is definitional rather than situational.

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

All Tommos 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