Skip to main content
Glama

Secure Autonomous Register

Recent signals

recent_signals
Read-onlyIdempotent

The Register's nightly stream of new primary records (vulnerability entries, recalls, rules) touching systems that act on their own, newest first. Signals never assign fault.

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": "recent_signals"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoKeep only one kind of record: vulnerability (a published vulnerability entry), report, disclosure, rule (a new or changed regulation), investigation or guidance. Leave out for all kinds.
limitNoHow many results to return, from 1 to 50. Default 10.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / kind / description
      Added value: +"Keep only one kind of record: vulnerability (a published vulnerability entry), report, disclosure, rule (a new or changed regulation), investigation or guidance. Leave out for all kinds."
    • addedInput schema / properties / kind / enum
      Added value: +[
      +  "vulnerability",
      +  "report",
      +  "disclosure",
      +  "rule",
      +  "investigation",
      +  "guidance"
      +]
    • addedInput schema / properties / limit / description
      Added value: +"How many results to return, from 1 to 50. Default 10."
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description does add genuinely new behavior: a nightly cadence (implying up to ~24h freshness, so today's items may be absent), newest-first ordering, and the semantic caveat that signals never assign fault. It stops short of describing pagination/cursor behavior or what an individual signal record contains, so it is additive but not rich.

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, front-loaded with the resource and cadence, with the no-fault caveat placed last as a reading constraint. There is little waste, though "The Register's" assumes context an agent may not have and the clause about "systems that act on their own" costs words without resolving scope precisely.

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 two-optional-parameter read-only feed with full schema coverage and annotations that cover safety and idempotency, this is nearly enough. The remaining gap is that with no output schema, the description still doesn't say what fields a signal carries or how a consumer should interpret it, which an agent may need to act on results.

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?

Schema description coverage is 100%, so both parameters (kind with a fully enumerated value list, and limit with default/min/max) are already self-documenting. The description adds nothing about either parameter — it does not say whether kind maps to the record types it names or how limit interacts with the nightly window. Baseline 3 is appropriate where the schema carries the semantics.

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 states a concrete resource and delivery shape: a nightly stream of new primary records (vulnerability entries, recalls, rules), newest first, scoped to autonomous systems. The verb is only implicit (a list/stream tool rather than "return" or "list"), and the "systems that act on their own" scoping is jargon an agent must interpret, but the core purpose is retrievable without opening the schema. Note it also names "recalls" as a record type while the schema's kind enum has no such value, a small internal mismatch.

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 guidance and no named alternative among siblings such as find_rules or search_cases. The closest thing to guidance is the implication that this surfaces newly published items, but an agent is left to infer that it should reach for this tool for discovery/triage rather than targeted lookup. No exclusions or prerequisites are given.

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