PRO: upcoming picks with positive model-vs-market edge. Needs a Pro key, via an Authorization: Bearer header (preferred) or the api_key argument.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Optional Pro API key (get one with /key in the Ledger FC Telegram bot). Preferred instead: send it as an Authorization: Bearer header, so it never enters the conversation. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / api_key / descriptionPrevious value: -"Pro API key (get one with /key in the Ledger FC Telegram bot)."New value: +"Optional Pro API key (get one with /key in the Ledger FC Telegram bot). Preferred instead: send it as an Authorization: Bearer header, so it never enters the conversation."Input schema / requiredPrevious value: -[
- "api_key"
-]New value: +[]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry behavioral weighting. It usefully discloses that the tool requires an authorization key, that the Authorization: Bearer header method is preferred, and that the api_key argument is a fallback. It does not disclose expected return shape, rate limits, or the read-only nature of the call, leaving some behavioral ambiguity.
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 only two sentences and wastes very few words. The 'PRO:' prefix is a bit cryptic and slightly redundant with the later 'Needs a Pro key,' but overall the structure is front-loaded with purpose and followed by authentication guidance.
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 one-parameter read-style tool, the description covers the key prereq and the edge-based selection criterion. However, with no output schema provided, the description does not hint at what fields or shape the response will take, and it gives limited contextual routing among sibling list-type tools.
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 already documents api_key well with a comment, and schema coverage is 100%, so the baseline is 3. The description adds an important semantic layer: the api_key parameter is not truly optional by itself because a key is required, and using the header is preferred over passing the key into the conversation. This clarifies how the optional parameter actually relates to the operation.
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 says the tool returns 'upcoming picks with positive model-vs-market edge,' which identifies both the resource (value bets) and the defining scope (positive edge). The verb 'get' is only in the tool name, not the description, but the phrase is specific enough to communicate what the tool does and to distinguish it from siblings like get_arbs or get_predictions.
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 implies it should be used when value bets with positive model-vs-market edge are needed and notes that a Pro key is required. However, it does not explicitly state when to prefer this tool over alternatives like get_predictions or get_arbs, nor does it provide concrete when-not-to-use guidance.
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.
Most tools target clearly distinct resources (predictions, bets, balance, leaderboard, record). However, get_predictions and get_value_bets are quite similar in scope—one being the unfiltered version of the other—so an agent could misselect without clearly reading paywalled requirements.
The get_ prefix is used for most retrieval operations, with place_bet, submit_prediction, fetch, and search as notable exceptions. The verb-noun structure is otherwise consistent, so the deviations are minor.
The 13-tool surface is proportional to the server's purpose of enabling paper betting, prediction retrieval, and performance tracking. Each tool maps to a distinct action within those workflows without feeling redundant.
The domain covers the full lifecycle: searching/fetching predictions, submitting and valuing predictions, placing and viewing bets, checking balance, and viewing performance via track record, CLV scores, and leaderboard. No obvious gaps prevent core workflows.