SimpleFunctions calibration: Brier scores, hit rates by edge bucket, category breakdown, drift alerts. Measured against resolved/settled markets.
| Name | Required | Description | Default |
|---|---|---|---|
| period | No | Period (30d, 90d, all) | |
| category | No | Topic filter (fed, elections, ai, crypto, sports, ...) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the burden of behavioral disclosure. It adds useful context by stating metrics are 'measured against resolved/settled markets', but it does not disclose potential side effects, cost, rate limits, or what 'drift alerts' entail. As a read-only getter, this is acceptable but not comprehensive.
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 a single, compact sentence that front-loads the domain and lists key metrics. It is efficient with no wasted words, though it could benefit from a clear sentence structure with a verb to improve readability.
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 read tool with two parameters and no output schema, the description gives a reasonable overview of the content but omits the return format and how parameters affect results. It also leaves domain terms like 'Brier scores' and 'edge bucket' undefined, which may be opaque to some agents.
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?
Schema description coverage is 100%, so the schema fully documents both parameters (period and category). The description adds no additional parameter semantics, but the baseline of 3 applies since the schema handles the meaning adequately.
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 identifies the tool's domain as 'SimpleFunctions calibration' and lists specific outputs (Brier scores, hit rates, category breakdown, drift alerts), which distinguishes it from sibling tools. However, it lacks an explicit verb like 'returns' or 'retrieves', so the purpose is stated implicitly rather than directly.
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 gives no guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. It simply describes what the tool provides, leaving the agent to infer appropriate usage from the name and output list.
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.
Many tools have overlapping purposes, such as multiple market query tools (scan_markets, screen_markets, get_market_detail, get_market_diff, get_market_history, inspect_ticker) and legislative tools (legislation, get_legislation, list_legislation, query_gov). Aliases like get_heartbeat_config/get_heartbeat_status and explore_public/explore_theses add further confusion. An agent would struggle to select the correct tool without deeply reading each description.
Most tools follow a verb_noun pattern (get_, list_, create_, update_), but there are notable deviations: 'legislation' lacks the 'get_' prefix, 'stt' and 'tts' are acronyms, 'monitor_the_situation' is a full phrase, and 'x_account/x_news/x_volume' use a non-standard prefix. The overall style is readable, but the mixed conventions reduce predictability.
108 tools is extreme for any server, even one covering prediction markets, trading, portfolio management, forum, skills, and speech. The massive surface area overwhelms agents and makes the server feel more like a platform than a coherent toolkit. This many tools inevitably leads to redundancy and maintenance burden.
The server covers an impressively broad domain: market data, thesis management, intents, strategies, positions, portfolio, forum, skills, legislative and economic queries, and audio/visual processing. Minor gaps exist (e.g., no delete for skills/theses, no update for some portfolio items) but core workflows are well-supported. Overall lifecycle coverage for most entities is strong.
