US companies ranked by what they do to their own share count. view=cannibals ranks the largest latest-fiscal-year repurchase as a share of market cap; view=diluters ranks the fastest 1-year share-count growth. Source: company filings. The buyback figure is cash spent on repurchases as reported, NOT net of new issuance. Values: cannibals, diluters.
| Name | Required | Description | Default |
|---|---|---|---|
| view | Yes | which leaderboard to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description complements the readOnlyHint annotation by providing additional behavioral clarity: it states the data source (company filings) and clarifies that the buyback figure is cash spent, not net of new issuance. This helps users understand the computation, though it does not detail any potential side effects (which are none given read-only).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is succinct, using a few sentences to convey the tool's purpose, both views, data source, and a critical clarification. There is no redundant information; each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description covers essential aspects: what it does, the parameter usage, and data nuances. It does not describe the output format, but given no output schema is provided, this is acceptable. The description is nearly complete for its scope.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema only provides 'view' with an enum and a brief description. The tool's description expands on each enum value (cannibals = largest repurchase as share of market cap; diluters = fastest share-count growth), giving full meaning. This significantly enhances understanding beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: ranking US companies by share-count changes (buybacks vs. dilution). It explicitly defines the two views (cannibals and diluters) with specific criteria. This is distinct from sibling tools like congress_trades or dca_rating, which focus on different financial topics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description effectively explains how to use the required 'view' parameter by detailing what each enum value returns. However, it does not explicitly contrast with alternative tools or provide context on when to choose this over others, though the distinct topic makes this less critical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct data source or analytical angle: buybacks, congress trades, DCA fit, insider buying, 13F filings, price levels, risk phrases, and options volume. There is no overlap in purpose or output, so an agent can unambiguously select the right tool.
All tool names follow a consistent lowercase_with_underscore noun-phrase pattern (e.g., buyback_leaders, risk_filings). The naming is uniform and descriptive, making it easy to predict what each tool does based on the name alone.
The server has 8 tools, squarely in the well-scoped range. Each tool represents a meaningful, non-redundant screen or data source, and none feels like filler or duplicative functionality.
For a market-aware server, the coverage is strong: it spans corporate actions (buybacks), insider activity, institutional holdings, technical levels, risk signals, and options flow. Minor gaps exist—no general price/quote tool or earnings-focused screen—but the set is coherent and covers diverse data sources without major dead ends.