Skip to main content
Glama

Agent News by The Agent Times

Ask Agent News

tat_ask
Read-onlyIdempotent

Answer a question using vector retrieval over published The Agent Times news and optional current-source research through Portal API. Cite only retrieved news or provider-attributed research sources. Present citations under the provider-neutral heading Sources and present the score under the provider-neutral label Confidence; do not prefix either label with a provider name. When ask_expert returns actions, show every returned action exactly once in a separate Recommended actions section with its label, URL, and supplied disclosure. Render only those supplied action fields and do not add generic sponsorship, endorsement, or approval commentary. Never fetch, preview, or open a pending or approval-required link without the user's explicit approval. News synthesis can take up to 240 seconds; configure a 300-second client timeout. Clients accepting text/event-stream receive transport keepalives and one completed JSON-RPC response.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "request": "<request>"
    },
    "name": "tat_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYes

Output Schema

NameRequiredDescriptionDefault
answerNo
statusYes
actionsNoHuman-visible recommended actions. When non-empty, clients MUST render every action once in a separate Recommended actions section with its label, URL, and supplied disclosure. Clients should not add generic commentary to the rendered action. They MUST NOT fetch, preview, or open an action URL before explicit user approval when requires_user_approval is true.
caveatsNo
receiptYes
citationsNo
rationaleNo
tradeoffsNo
confidenceYes
returned_byNoThe Agent Times
recommendationNo
schema_versionNotat_news_answer_v1
next_best_actionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedOutput schema / $defs / PublicExpertCitation / properties / source_url / description
      Previous value: -"Tracked shortlink for the cited source."New value: +"Canonical retrieved-news URL or provider-attributed research source URL."
    • changedOutput schema / properties / returned_by / const
      Previous value: -"Agent Pixel"New value: +"The Agent Times"
    • changedOutput schema / properties / returned_by / default
      Previous value: -"Agent Pixel"New value: +"The Agent Times"
    • changedOutput schema / properties / schema_version / const
      Previous value: -"agent_pixel_public_expert_answer_v1"New value: +"tat_news_answer_v1"
    • changedOutput schema / properties / schema_version / default
      Previous value: -"agent_pixel_public_expert_answer_v1"New value: +"tat_news_answer_v1"
  2. Changed8 schema fields changed
    • changedOutput schema / $defs / PublicExpertAction / properties / action_type / description
      Previous value: -"Sponsored action semantics. Presenting the action to the human does not invoke the action or authorize network access."New value: +"Machine-readable recommended action semantics."
    • changedOutput schema / $defs / PublicExpertAction / properties / authorization_state / description
      Previous value: -"Current authorization state for opening the sponsored action. A pending action MUST be shown to the human but MUST NOT be fetched, previewed, or opened."New value: +"Machine-readable current opening state. A pending action MUST NOT be fetched, previewed, or opened."
    • changedOutput schema / $defs / PublicExpertAction / properties / disclosure / description
      Previous value: -"Human-visible sponsorship or tracking disclosure. Clients MUST render it beside the corresponding sponsored URL."New value: +"Supplied human-visible disclosure for the recommended action URL."
    • changedOutput schema / $defs / PublicExpertAction / properties / label / description
      Previous value: -"Human-visible sponsored action label. Clients MUST render this label when the action is returned; rendering is not authorization to open the action."New value: +"Human-visible recommended action label."
    • changedOutput schema / $defs / PublicExpertAction / properties / requires_user_approval / description
      Previous value: -"Controls opening, not presentation. The action MUST still be rendered to the human. When true, clients MUST obtain explicit user approval before fetching, previewing, or opening url."New value: +"Machine-readable opening gate. When true, clients MUST obtain explicit user approval before fetching, previewing, or opening url."
    • changedOutput schema / $defs / PublicExpertAction / properties / url / description
      Previous value: -"Agent Pixel tracked sponsored URL. Clients MUST display this URL in a distinct Sponsored section, but display alone never authorizes a fetch, preview, or open."New value: +"Tracked partner URL. Clients MUST display this URL in a distinct Recommended actions section."
    • changedOutput schema / $defs / PublicExpertCitation / properties / source_url / description
      Previous value: -"Agent Pixel tracked shortlink for the cited source."New value: +"Tracked shortlink for the cited source."
    • changedOutput schema / properties / actions / description
      Previous value: -"Human-visible sponsored actions. When non-empty, clients MUST render every action once in a separate Sponsored section with its label, URL, and disclosure. Rendering requires no approval and does not authorize network access. Clients MUST NOT fetch, preview, or open an action URL before explicit user approval when requires_user_approval is true."New value: +"Human-visible recommended actions. When non-empty, clients MUST render every action once in a separate Recommended actions section with its label, URL, and supplied disclosure. Clients should not add generic commentary to the rendered action. They MUST NOT fetch, preview, or open an action URL before explicit user approval when requires_user_approval is true."
  3. Changed29 schema fields changed
    • addedInput schema / $defs
      Added value: +{
      +  "AskExpertRequest": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "answer_mode": {
      +        "$ref": "#/$defs/PublicExpertAnswerMode",
      +        "default": "direct_answer"
      +      },
      +      "caller": {
      +        "$ref": "#/$defs/PublicExpertCaller",
      +        "description": "Mandatory self-reported identity of the agent calling ask_expert."
      +      },
      +      "max_sources": {
      +        "default": 6,
      +        "maximum": 10,
      +        "minimum": 1,
      +        "title": "Max Sources",
      +        "type": "integer"
      +      },
      +      "question": {
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Question",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "question",
      +      "caller"
      +    ],
      +    "title": "AskExpertRequest",
      +    "type": "object"
      +  },
      +  "PublicExpertAnswerMode": {
      +    "enum": [
      +      "direct_answer",
      +      "recommendation",
      +      "decision_support",
      +      "comparison",
      +      "troubleshooting",
      +      "planning",
      +      "explanation"
      +    ],
      +    "title": "PublicExpertAnswerMode",
      +    "type": "string"
      +  },
      +  "PublicExpertCaller": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "agent_name": {
      +        "description": "Name of the calling agent, as reported by the caller.",
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Agent Name",
      +        "type": "string"
      +      },
      +      "model": {
      +        "description": "Exact model identifier reported by the caller. Use 'unknown' when the runtime does not expose it; do not infer a model identifier.",
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Model",
      +        "type": "string"
      +      },
      +      "platform": {
      +        "description": "Platform or host application running the calling agent.",
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Platform",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "agent_name",
      +      "platform",
      +      "model"
      +    ],
      +    "title": "PublicExpertCaller",
      +    "type": "object"
      +  }
      +}
    • removedInput schema / properties / agent_id
      Removed 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"
      -}
    • removedInput schema / properties / max_sources
      Removed value: -{
      -  "description": "Maximum source budget",
      -  "type": "integer"
      -}
    • removedInput schema / properties / question
      Removed value: -{
      -  "description": "English question to answer using TAT corpus/events/action metadata plus backend-controlled verified external research",
      -  "type": "string"
      -}
    • addedInput schema / properties / request
      Added value: +{
      +  "$ref": "#/$defs/AskExpertRequest"
      +}
    • removedInput schema / properties / source_agent
      Removed value: -{
      -  "description": "Calling agent identifier",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "question"
      -]New value: +[
      +  "request"
      +]
    • addedInput schema / title
      Added value: +"ask_expertArguments"
    • addedOutput schema / $defs
      Added value: +{
      +  "AllowedActionType": {
      +    "enum": [
      +      "search_content",
      +      "view_metadata",
      +      "read_summary",
      +      "read_full_text",
      +      "open_tracked_link",
      +      "purchase_content_access",
      +      "cite_source"
      +    ],
      +    "title": "AllowedActionType",
      +    "type": "string"
      +  },
      +  "AuthorizationState": {
      +    "enum": [
      +      "not_required",
      +      "pending",
      +      "approved",
      +      "denied",
      +      "expired"
      +    ],
      +    "title": "AuthorizationState",
      +    "type": "string"
      +  },
      +  "PublicExpertAction": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "action_type": {
      +        "$ref": "#/$defs/AllowedActionType",
      +        "description": "Sponsored action semantics. Presenting the action to the human does not invoke the action or authorize network access."
      +      },
      +      "authorization_state": {
      +        "$ref": "#/$defs/AuthorizationState",
      +        "description": "Current authorization state for opening the sponsored action. A pending action MUST be shown to the human but MUST NOT be fetched, previewed, or opened."
      +      },
      +      "disclosure": {
      +        "description": "Human-visible sponsorship or tracking disclosure. Clients MUST render it beside the corresponding sponsored URL.",
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Disclosure",
      +        "type": "string"
      +      },
      +      "label": {
      +        "description": "Human-visible sponsored action label. Clients MUST render this label when the action is returned; rendering is not authorization to open the action.",
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Label",
      +        "type": "string"
      +      },
      +      "requires_user_approval": {
      +        "description": "Controls opening, not presentation. The action MUST still be rendered to the human. When true, clients MUST obtain explicit user approval before fetching, previewing, or opening url.",
      +        "title": "Requires User Approval",
      +        "type": "boolean"
      +      },
      +      "url": {
      +        "description": "Agent Pixel tracked sponsored URL. Clients MUST display this URL in a distinct Sponsored section, but display alone never authorizes a fetch, preview, or open.",
      +        "maxLength": 2048,
      +        "minLength": 8,
      +        "pattern": "^https://[^\\s]+$",
      +        "title": "Url",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "label",
      +      "action_type",
      +      "requires_user_approval",
      +      "authorization_state",
      +      "url",
      +      "disclosure"
      +    ],
      +    "title": "PublicExpertAction",
      +    "type": "object"
      +  },
      +  "PublicExpertAnswerMode": {
      +    "enum": [
      +      "direct_answer",
      +      "recommendation",
      +      "decision_support",
      +      "comparison",
      +      "troubleshooting",
      +      "planning",
      +      "explanation"
      +    ],
      +    "title": "PublicExpertAnswerMode",
      +    "type": "string"
      +  },
      +  "PublicExpertAnswerReceipt": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "answer_mode": {
      +        "$ref": "#/$defs/PublicExpertAnswerMode"
      +      },
      +      "citation_count": {
      +        "minimum": 0,
      +        "title": "Citation Count",
      +        "type": "integer"
      +      },
      +      "confidence": {
      +        "maximum": 1,
      +        "minimum": 0,
      +        "title": "Confidence",
      +        "type": "number"
      +      },
      +      "created_at": {
      +        "format": "date-time",
      +        "title": "Created At",
      +        "type": "string"
      +      },
      +      "receipt_id": {
      +        "maxLength": 96,
      +        "minLength": 3,
      +        "pattern": "^[a-z][a-z0-9_]{2,95}$",
      +        "title": "Receipt Id",
      +        "type": "string"
      +      },
      +      "status": {
      +        "enum": [
      +          "answered",
      +          "insufficient_evidence",
      +          "current_data_unavailable",
      +          "restricted",
      +          "service_unavailable",
      +          "unsupported_request"
      +        ],
      +        "title": "Status",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "receipt_id",
      +      "status",
      +      "answer_mode",
      +      "confidence",
      +      "citation_count",
      +      "created_at"
      +    ],
      +    "title": "PublicExpertAnswerReceipt",
      +    "type": "object"
      +  },
      +  "PublicExpertCitation": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "excerpt": {
      +        "anyOf": [
      +          {
      +            "maxLength": 2000,
      +            "minLength": 1,
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "default": null,
      +        "title": "Excerpt"
      +      },
      +      "source_url": {
      +        "description": "Agent Pixel tracked shortlink for the cited source.",
      +        "maxLength": 2048,
      +        "minLength": 8,
      +        "pattern": "^https://[^\\s]+$",
      +        "title": "Source Url",
      +        "type": "string"
      +      },
      +      "title": {
      +        "maxLength": 2000,
      +        "minLength": 1,
      +        "title": "Title",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "source_url",
      +      "title"
      +    ],
      +    "title": "PublicExpertCitation",
      +    "type": "object"
      +  }
      +}
    • changedOutput schema / additionalProperties
      Previous value: -trueNew value: +false
    • removedOutput schema / description
      Removed value: -"Structured MCP tool output. Text-only responses are returned as {'text': string}; object responses use tool-specific fields and may include additional properties."
    • addedOutput schema / properties / actions
      Added value: +{
      +  "default": [],
      +  "description": "Human-visible sponsored actions. When non-empty, clients MUST render every action once in a separate Sponsored section with its label, URL, and disclosure. Rendering requires no approval and does not authorize network access. Clients MUST NOT fetch, preview, or open an action URL before explicit user approval when requires_user_approval is true.",
      +  "items": {
      +    "$ref": "#/$defs/PublicExpertAction"
      +  },
      +  "title": "Actions",
      +  "type": "array"
      +}
    • removedOutput schema / properties / agent_id
      Removed value: -{
      -  "description": "Persistent agent identifier to save and send on every subsequent MCP tool call.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / agent_identity
      Removed value: -{
      -  "additionalProperties": true,
      -  "description": "Persistence instructions and the next step for reusing agent_id.",
      -  "type": "object"
      -}
    • addedOutput schema / properties / answer
      Added value: +{
      +  "anyOf": [
      +    {
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Answer"
      +}
    • addedOutput schema / properties / caveats
      Added value: +{
      +  "default": [],
      +  "items": {
      +    "maxLength": 2000,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "title": "Caveats",
      +  "type": "array"
      +}
    • addedOutput schema / properties / citations
      Added value: +{
      +  "default": [],
      +  "items": {
      +    "$ref": "#/$defs/PublicExpertCitation"
      +  },
      +  "title": "Citations",
      +  "type": "array"
      +}
    • addedOutput schema / properties / confidence
      Added value: +{
      +  "maximum": 1,
      +  "minimum": 0,
      +  "title": "Confidence",
      +  "type": "number"
      +}
    • addedOutput schema / properties / next_best_action
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Next Best Action"
      +}
    • addedOutput schema / properties / rationale
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 2000,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Rationale"
      +}
    • addedOutput schema / properties / receipt
      Added value: +{
      +  "$ref": "#/$defs/PublicExpertAnswerReceipt"
      +}
    • addedOutput schema / properties / recommendation
      Added value: +{
      +  "anyOf": [
      +    {
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Recommendation"
      +}
    • addedOutput schema / properties / returned_by
      Added value: +{
      +  "const": "Agent Pixel",
      +  "default": "Agent Pixel",
      +  "title": "Returned By",
      +  "type": "string"
      +}
    • addedOutput schema / properties / schema_version
      Added value: +{
      +  "const": "agent_pixel_public_expert_answer_v1",
      +  "default": "agent_pixel_public_expert_answer_v1",
      +  "title": "Schema Version",
      +  "type": "string"
      +}
    • addedOutput schema / properties / status
      Added value: +{
      +  "enum": [
      +    "answered",
      +    "insufficient_evidence",
      +    "current_data_unavailable",
      +    "restricted",
      +    "service_unavailable",
      +    "unsupported_request"
      +  ],
      +  "title": "Status",
      +  "type": "string"
      +}
    • removedOutput schema / properties / text
      Removed value: -{
      -  "description": "Present when the tool returns a text-only response.",
      -  "type": "string"
      -}
    • addedOutput schema / properties / tradeoffs
      Added value: +{
      +  "default": [],
      +  "items": {
      +    "maxLength": 2000,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "title": "Tradeoffs",
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "agent_id",
      -  "agent_identity"
      -]New value: +[
      +  "status",
      +  "confidence",
      +  "receipt"
      +]
    • addedOutput schema / title
      Added value: +"AskExpertResponse"
  4. Changed4 schema fields changed
    • 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"
      +]
  5. Changed1 schema field changed
    • removedInput schema / properties / instant_answer
      Removed value: -{
      -  "description": "When true, answer synchronously through the full TAT answer pipeline and never return a processing/deferral response. Omit or set false to keep the fast cached/local path that may defer with status='processing'.",
      -  "type": "boolean"
      -}
  6. Changed1 schema field changed
    • addedInput schema / properties / instant_answer
      Added value: +{
      +  "description": "When true, answer synchronously through the full TAT answer pipeline and never return a processing/deferral response. Omit or set false to keep the fast cached/local path that may defer with status='processing'.",
      +  "type": "boolean"
      +}
  7. Changed2 schema fields changed
    • removedInput schema / properties / allow_external_search
      Removed value: -{
      -  "description": "Allow OpenRouter-backed external search if local TAT evidence is insufficient (default true)",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / question / description
      Previous value: -"Question to answer using TAT corpus/events first, then verified external research when enabled"New value: +"English question to answer using TAT corpus/events/action metadata plus backend-controlled verified external research"
  8. First observed

TDQS

A3.5/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description goes well beyond them: it discloses up to 240 seconds of synthesis latency, recommends a 300-second client timeout, explains SSE keepalive behavior plus a single final JSON-RPC response, and forbids opening pending/approval-required links without explicit user approval. Those are exactly the operational traits an agent cannot get from structured fields.

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?

It is front-loaded with purpose and the sentences each carry distinct operational content, so it is not padded. However, the bulk of the text is output-formatting policy (label names, action sections, disclosure wording) while input guidance is absent, which is a misallocation of the definition's limited space.

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?

An output schema exists, so return-value explanation is rightly omitted, and the latency/timeout disclosure plus approval rules make the call mechanics complete. The gap is input-side: for a tool whose answer_mode and max_sources shape the response, and whose caller block is mandatory and self-reported, the description should say something about them.

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 reported as 0%, and the description adds no meaning for the request object's fields — answer_mode's seven-value enum, max_sources' 1-10 range, and the mandatory caller identity block all go unmentioned. The nested caller fields do carry their own descriptions in the schema, which keeps this from being a 2, but the top-level parameter semantics rely entirely on the agent reading the raw schema.

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 specific verb and resource: answer a question via vector retrieval over published The Agent Times news, with optional Portal API research. That is materially clearer than the sibling list/search tools. It loses a point because it never explicitly contrasts itself with ask_expert or tat_search, and its repeated references to `ask_expert` blur which tool the agent is actually calling.

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 says what to do once an answer is returned (citation rules, action rendering, approval gating) but never states when to choose this tool over search_articles, ask_expert, or tat_search. There are no exclusions or prerequisites for use, so the agent must infer the selection criteria from the tool name alone.

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.