signal-bureau

get_signals

START HERE for browsing — the cheap read (500/day, no model work). The full machine-readable signal feed (same payload as GET /api/signals): every entity currently flagged by the attention engine, with trajectory, domains, desk membership, and an explicit evidenceStatus (receipted rows carry source-attributed evidence URLs; unreceipted rows are labeled leads). Measured property: Measured association: flagged markets repriced materially at 1.52x the rate of matched unflagged controls (95% CI 1.22-1.73, shock-days excluded, controls reweighted to the flagged cohort; n=2039 flagged vs 84517 controls, window 2026-03-29 to 2026-09-05, as of 2026-09-05). An attention-leads-movement association — never a directional claim.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	How many signals (default all flagged)
`direction`	No	Filter by trajectory: rising\|fading\|steady\|new

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedAug 17, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does substantial work: it discloses the quota (500/day), read-only nature ('cheap read'), payload contents, the distinction between receipted and unreceipted evidence rows, and an explicit caveat that the association is never directional. Only minor invocation details like sorting or pagination behavior are absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening is well front-loaded and useful, but the long 'Measured property: Measured association...' statistical block, including the duplicative 'Measured' label, is tangential to invoking the tool and bloats the description.

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?

For a simple tool with no output schema and no annotations, the description is adequately complete: it states what the feed contains, how evidenceStatus behaves, the associated quota, and even hedges the interpretation of the signal. It does not give explicit return formatting, but 'machine-readable feed' plus the field list covers the essential agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema coverage is 100%, so the schema already documents both parameters. The description reinforces the 'limit' default indirectly and mentions trajectory as an output field, but adds no new syntax or value semantics beyond what the schema provides.

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?

Description opens with 'START HERE for browsing' and identifies the resource as the full machine-readable signal feed of every entity currently flagged by the attention engine. It lists payload fields (trajectory, domains, desk membership, evidenceStatus), making the purpose concrete. However, it does not explicitly name sibling tools to contrast with, so differentiation relies mostly on the 'full feed' and 'cheap read' phrasing.

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?

'START HERE for browsing' and 'the cheap read (500/day, no model work)' provide clear positive usage context and set expectations for when to use this tool. It does not state exclusions or point to alternatives such as get_desk_feed or top_accelerating, so it falls short of the most explicit route-it guidance.

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

All signal-bureau tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool targets a distinct function: ask is async event queries, get_answer retrieves results, get_signals and top_accelerating provide different signal views, get_entity and search_entities cover entity details and search, etc. No two tools have overlapping purposes, and descriptions clearly separate them.

Naming Consistency4/5

The majority of tools follow a 'get_' prefix for retrieval (13 of 21) and other clear verbs like 'ask', 'create_order', 'propose_topic', 'send_feedback'. A few use noun phrases like 'todays_brief' and 'top_accelerating', which breaks the pattern slightly but are still intuitive. Overall consistent and predictable.

Tool Count5/5

21 tools cover the full scope of the server: exploration, querying, ordering, account management, feedback, and data records. Each tool serves a clear purpose without redundancy, and the count feels well-scoped for the domain.

Completeness4/5

The tool surface covers all major workflows: browsing signals, asking questions, getting detailed reports, ordering, providing feedback, and proposing new topics. Minor gaps exist (e.g., no explicit tool to cancel an order or manage watched topics directly), but core operations are present and agents can handle the domain effectively.

Resources

Need Help?