Skip to main content
Glama
SlothyAfk

finance-pulse

by SlothyAfk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Find developments

find_topics
Read-onlyIdempotent

Find and rank developments for a symbol, sector, theme or storyline, sorted by momentum, volume or recency. Use it to discover what is trending or browse a storyline in order.

Instructions

List developments for a symbol, sector, theme or storyline. sort=velocity: most statements in the last 24 hours; size: most statements; recent: latest statement first. symbol: comma-separate several (OR). Topics with fewer than 3 statements are left out unless you lower min_statements, so an empty list can mean "only small ones": retry with min_statements=1. With storyline_id every topic of the storyline is listed by default (sort="oldest" gives them in order).

Input Schema

NameRequiredDescriptionDefault
sortNovelocity
limitNoHow many to return per call; use the cursor for more
cursorNonext_cursor from the previous call, for the next page; keep every other argument the same
sectorNoGICS sector
symbolNoTicker or entity code, e.g. NVDA. Comma-separate several (OR).
theme_idNoTheme id from `themes` or `reference`
storyline_idNoStoryline id, as returned by `storylines`, `get_symbol` or a topic's storylines
min_statementsNoLeave out developments with fewer statements. Default: 3, or 1 with storyline_id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.2.1
    • changedInput schema / properties / cursor / description
      Previous value: -"next_cursor from the previous call, for the next page"New value: +"next_cursor from the previous call, for the next page; keep every other argument the same"
    • changedInput schema / properties / limit / description
      Previous value: -"How many to return, 1-100"New value: +"How many to return per call; use the cursor for more"
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +50
    • addedInput schema / properties / min_statements / anyOf
      Added value: +[
+  {
+    "minimum": 1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / min_statements / default
      Previous value: -3New value: +null
    • changedInput schema / properties / min_statements / description
      Previous value: -"Leave out developments with fewer statements"New value: +"Leave out developments with fewer statements. Default: 3, or 1 with storyline_id"
    • removedInput schema / properties / min_statements / minimum
      Removed value: -1
    • removedInput schema / properties / min_statements / type
      Removed value: -"integer"
    • addedInput schema / properties / storyline_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Storyline id, as returned by `storylines`, `get_symbol` or a topic's storylines",
+  "title": "Storyline Id"
+}
    • changedInput schema / properties / symbol / description
      Previous value: -"Ticker or entity code, e.g. NVDA. Comma-separate several (OR), up to 10."New value: +"Ticker or entity code, e.g. NVDA. Comma-separate several (OR)."
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), yet the description still adds non-obvious behavior: the silent 3-statement drop threshold, the fact that an empty result may mean "only small ones", and that a storyline_id query silently changes the default sort. Those are the exact gotchas that would otherwise cause a wrong conclusion from an empty page.

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?

Purpose is front-loaded in the first clause, then each following clause handles one concern (sort, symbols, threshold, storyline default) with no filler or repetition. Dense but every sentence carries a distinct, actionable fact.

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 an 8-parameter, all-optional listing tool with no output schema, the description covers the traps that matter: filtering, threshold behavior, sort semantics, and storyline default ordering. Pagination is deferred entirely to the schema's `cursor`/`limit` descriptions, and the shape of a returned topic is never sketched, which is the only real gap.

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

Parameters4/5

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

Schema coverage is high (88%), so the baseline is 3, and the description earns the extra point by defining what the bare `sort` enum members actually mean (velocity = most statements in the last 24h, size = most statements, recent = latest first, oldest) — information the schema does not carry. It also reinforces the min_statements default split and the comma-OR behavior for symbol.

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 ("List developments") plus the four filter axes (symbol, sector, theme, storyline), so an agent knows exactly what the tool returns. It never names a sibling like `trending` or `search_statements` to contrast against, so differentiation from the rest of the family is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is real operational guidance — which sort mode to pick, the 3-statement default threshold, and the explicit recovery step ("retry with min_statements=1") when a list comes back empty. What is missing is tool-selection guidance: nothing says when to reach for this instead of `trending`, `search_statements`, or `storylines`.

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

Deploy Server

Other Tools