Agent News by The Agent Times

Recommend Agent Tools

tat_recommend

Read-onlyIdempotent

Return sourced recommendations for an agent/operator use case using TAT trusted corpus, events, and answer standard. Not an external-resource safety checker.

Input Schema

TableJSON Schema

Name	Required	Description
`agent_id`	No	Optional persistent agent identifier. On the first MCP tool call that accepts agent_id, omit this field; the response will return a generated agent_id. Save that value and send it in agent_id only on subsequent MCP tool calls that accept agent_id. Never add agent_id to ask_expert or tat_ask. Any stable string is accepted.
`use_case`	Yes	Agent/operator use case
`constraints`	No	Optional constraints
`source_agent`	No	Calling agent identifier

Output Schema

TableJSON Schema

Name	Required	Description
`text`	No	Present when the tool returns a text-only response.
`agent_id`	Yes	Persistent agent identifier to save and send only on subsequent MCP tool calls that accept agent_id. Never add agent_id to ask_expert or tat_ask.
`agent_identity`	Yes	Persistence instructions and the next step for reusing agent_id.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 23, 2026

changedInput schema / properties / agent_id / description

Previous value: -"Optional persistent agent identifier. On the first MCP tool call, omit this field; the response will return a generated agent_id. Save that value and send it in agent_id on every subsequent MCP tool call. Any stable string is accepted."New value: +"Optional persistent agent identifier. On the first MCP tool call that accepts agent_id, omit this field; the response will return a generated agent_id. Save that value and send it in agent_id only on subsequent MCP tool calls that accept agent_id. Never add agent_id to ask_expert or tat_ask. Any stable string is accepted."

changedOutput schema / properties / agent_id / description

Previous value: -"Persistent agent identifier to save and send on every subsequent MCP tool call."New value: +"Persistent agent identifier to save and send only on subsequent MCP tool calls that accept agent_id. Never add agent_id to ask_expert or tat_ask."

Changed4 schema fields changedAug 2, 2026

addedInput schema / properties / agent_id

Added value: +{
+  "description": "Optional persistent agent identifier. On the first MCP tool call, omit this field; the response will return a generated agent_id. Save that value and send it in agent_id on every subsequent MCP tool call. Any stable string is accepted.",
+  "type": "string"
+}

addedOutput schema / properties / agent_id

Added value: +{
+  "description": "Persistent agent identifier to save and send on every subsequent MCP tool call.",
+  "type": "string"
+}

addedOutput schema / properties / agent_identity

Added value: +{
+  "additionalProperties": true,
+  "description": "Persistence instructions and the next step for reusing agent_id.",
+  "type": "object"
+}

addedOutput schema / required

Added value: +[
+  "agent_id",
+  "agent_identity"
+]

Changed1 schema field changedMay 15, 2026

removedInput schema / properties / allow_external_search

Removed value: -{
-  "description": "Allow OpenRouter-backed external search (default true)",
-  "type": "boolean"
-}

First observedMay 11, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds that recommendations are 'sourced' and drawn from 'TAT trusted corpus, events, and answer standard', and clarifies it is not a safety checker. This gives useful context beyond the annotations without contradicting them.

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

Conciseness5/5

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

Two sentences with no filler. The core action and scope are front-loaded, and the negative boundary is a single clause. Every word adds value.

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?

The description, paired with a complete schema and rich annotations, is sufficient for an agent to know what the tool does and roughly when to call it. The output schema exists, so return format doesn't need to be described. It doesn't provide examples, but neither the complexity of the parameters nor the absence of structured data demands more.

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 the schema fully documents agent_id, use_case, constraints, and source_agent. The description does not delve into parameter semantics, which is acceptable given the high coverage; it earns the baseline of 3.

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 opens with a specific action 'Return sourced recommendations' and identifies the target use case ('agent/operator use case') plus the source corpora ('TAT trusted corpus, events, and answer standard'). The second sentence draws a clear boundary ('Not an external-resource safety checker'), which helps distinguish it from unrelated checks, but it does not name a sibling tool explicitly.

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 scopes the tool to agent/operator use cases, which tells an agent when to reach for it, and warns that it is not an external-resource safety checker, giving a when-not. It does not mention alternative sibling tools such as tat_ask or ask_expert, so it stops short of full routing guidance.

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

All Agent News by The Agent Times tools Inspect

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.