Skip to main content
Glama

search_announcements

Read-onlyIdempotent

Full-text search across NZX market announcements (2017-present), most with extracted PDF text. Searches announcement titles AND full document content. Use for finding mentions of specific topics, companies, people, or events across all NZX filings. Results include: ai_category (25-category AI classification like M&A, Dividend, Regulatory, Capital Raise, Guidance, Earnings Results), ai_category_confidence (0.0-1.0), ai_sub_topics (1-3 topic tags). May also include: ai_sentiment (positive/negative/neutral/mixed), ai_sentiment_score (-1.0 to 1.0), ai_topics (array of topic labels), ai_risk_flags (array of risk indicators like profit_warning, dividend_cut), and ai_summary (concise summary).

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": "search_announcements"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoSearch query — searches both titles and full PDF document text
toNoEnd date (YYYY-MM-DD)
fromNoStart date (YYYY-MM-DD)
typeNoAnnouncement type: FLLYR, HALFYR, SHINTR, MEETING, GENERAL, SECISSUE, DVDEND, etc.
limitNoMax results (default 20)
tickerNoFilter by company ticker

Output Schema

NameRequiredDescriptionDefault
dataYesThe tool payload. Null when the call did not produce one — read meta.availability_status to find out why, and do not treat null as zero, empty or "none found".
metaYes
toolYesTool that produced this result.
schema_versionYesEnvelope contract version. Bumps only on a breaking shape change.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / meta / properties / provenance / description
      Previous value: -"Whether the figures can cite a source document. \"undeclared\" means no claim has been made for this endpoint yet — it is not a claim that the data is unsourced."New value: +"Whether the figures can cite a source document. \"direct\": every returned row carries its own document URL (see meta.sources). \"reachable\": some do, or the documents sit beside figures that are not rows. \"undeclared\": no document URL was found in this payload — it is not a claim that the data is unsourced."
    • addedOutput schema / properties / meta / properties / sources
      Added value: +{
      +  "description": "Primary documents (NZX announcements, annual reports) whose URLs appear in this payload. Cite these with their date when you quote a figure. A listed document was returned with the data; it is not proof that a given sentence of your answer came from it.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "date": {
      +        "description": "YYYY-MM-DD, or null when the row has no date.",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "kind": {
      +        "enum": [
      +          "announcement",
      +          "annual_report",
      +          "document"
      +        ],
      +        "type": "string"
      +      },
      +      "title": {
      +        "type": "string"
      +      },
      +      "url": {
      +        "format": "uri",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "url",
      +      "title",
      +      "date",
      +      "kind"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  2. Changed4 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • changedInput schema / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "data": {
      +      "description": "The tool payload. Null when the call did not produce one — read meta.availability_status to find out why, and do not treat null as zero, empty or \"none found\"."
      +    },
      +    "meta": {
      +      "additionalProperties": true,
      +      "properties": {
      +        "availability_status": {
      +          "description": "ok: complete payload. truncated: payload exceeded the transport cap and was cut. parse_failed: payload is text this server could not parse as JSON. error: the tool raised.",
      +          "enum": [
      +            "ok",
      +            "truncated",
      +            "parse_failed",
      +            "error"
      +          ],
      +          "type": "string"
      +        },
      +        "encoding": {
      +          "description": "toon = pipe-delimited tabular encoding; header row names the columns.",
      +          "enum": [
      +            "json",
      +            "toon"
      +          ],
      +          "type": "string"
      +        },
      +        "provenance": {
      +          "description": "Whether the figures can cite a source document. \"undeclared\" means no claim has been made for this endpoint yet — it is not a claim that the data is unsourced.",
      +          "enum": [
      +            "direct",
      +            "label",
      +            "reachable",
      +            "none",
      +            "undeclared"
      +          ],
      +          "type": "string"
      +        },
      +        "retrieved_at": {
      +          "description": "When this platform produced the answer — NOT the as-at date of the data.",
      +          "format": "date-time",
      +          "type": "string"
      +        },
      +        "warnings": {
      +          "items": {
      +            "type": "string"
      +          },
      +          "type": "array"
      +        }
      +      },
      +      "required": [
      +        "retrieved_at",
      +        "availability_status",
      +        "provenance"
      +      ],
      +      "type": "object"
      +    },
      +    "schema_version": {
      +      "description": "Envelope contract version. Bumps only on a breaking shape change.",
      +      "type": "string"
      +    },
      +    "tool": {
      +      "description": "Tool that produced this result.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "schema_version",
      +    "tool",
      +    "data",
      +    "meta"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful disclosure — the 2017-present coverage window and the caveat that only 'most' documents have extracted PDF text, implying incomplete full-text coverage. However, the bulk of the text enumerates return fields that a dedicated output schema already supplies, so the added behavioral value is modest.

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?

Scope and usage are front-loaded in the first two sentences, which is good. The remaining half of the description is a long enumeration of ai_* result fields that duplicates the output schema and dilutes the actionable content.

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 all six parameters optional, full schema coverage, annotations and an output schema, the description covers scope, query semantics and data caveats adequately. The main shortfall is not routing the agent away from overlapping search siblings, and spending its length on return fields rather than that distinction.

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 baseline is 3. The description's only parameter-relevant statement, that queries hit both titles and full PDF text, merely restates what the `q` schema description already says; date bounds, type codes, limit and ticker are left entirely to the 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?

Names a specific verb and resource plus scope: 'Full-text search across NZX market announcements (2017-present)' over both titles and extracted PDF text. An agent knows exactly what it queries, but nothing in the text differentiates it from siblings like search_semantic or get_announcement_sentiment, which also surface announcement content.

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?

'Use for finding mentions of specific topics, companies, people, or events across all NZX filings' gives clear when-to-use context. It stops short of when-not-to-use guidance or naming an alternative for semantic or sentiment-oriented lookups.

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.