Skip to main content
Glama

Tommos

Read the first look

read_the_first_look
Read-onlyIdempotent

The first look reads the last 30 days of mail and meetings and files cards on the conversations still open. Before it starts: whether it may start (reasons, each with a key, the words and the page where it is put right; why_not is the same words), and what it will read (records, threads, meetings). reads.mail says how far the last 30 days of mail have arrived (not_begun, arriving, arrived) and reads.meetings_arrival says the same for the meetings of the workspace's source; it cannot start while either is arriving. meetings says whether the owner answered about the source of meetings (set, skipped or not_asked): it cannot start while not_asked, and when skipped it reads mail only (reads.mail_only). reads.leads_waiting_for_the_yes is how many leads Tommo made from the 30 days of a mailbox connected at the start: no run is made for one of them before the first look starts. It may start once a mailbox is connected and the workspace is in its first 14 days or on a plan. Once started: its progress, with the runs done, waiting, failed and stopped, each run that did not end done with the reason it recorded (runs_not_done), and the cards filed. The runs count a record whose run was already going when the first look started. ended says that no run of it waits (queued is how many runs it queued at its start). cards_waiting_for_a_person is what waits for a person's decision in Flow now, and what_waits_in_flow is the same count by kind.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds domain context (it does not start a run; it cannot start while mail/meetings are 'arriving'), but says nothing about the tool call itself such as auth, rate limits, or caching, hence a baseline 3.

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 sprawling, jargon-dense paragraph full of undefined internal terms (Tommo, Flow, leads, cards, why_not, reads.mail_only) that an agent must parse to find anything actionable. It is far larger than needed for a zero-parameter read tool and buries the purpose in domain state enumeration.

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?

With no output schema, the description carries the burden of describing what is returned and it does enumerate the response fields (why_not, reads.mail, reads.meetings_arrival, runs_not_done, ended, cards_waiting_for_a_person, what_waits_in_flow). That is genuinely useful compensation for the missing output schema, even if the field names are opaque.

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?

The tool takes zero parameters and the schema is empty with 100% coverage, so there is nothing for the description to disambiguate. Baseline 4 applies.

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 sentence gives a concrete verb+resource: it 'reads the last 30 days of mail and meetings and files cards on the conversations still open,' and the rest clarifies it returns readiness and progress state. It is clear what the tool does, but it never names its obvious sibling start_the_first_look, so the agent must infer the read/write split from names alone.

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?

The description is saturated with domain conditions (when the first look may start) but never says when an agent should call this tool versus start_the_first_look or read_the_workspace_state. There are no exclusions, prerequisites for invocation, or alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources