apex_run_dynamic_penaltyAdvisory cooldown and size-penalty hints from a recent loss streak: returns size_multiplier, cooldown_sec, and severity. Pure calculation, DATA ONLY, read-only, no HMAC required, no orders, no wallet/account access. Not trading advice.
| Name | Required | Description | Default |
|---|---|---|---|
| recent_net_pnl | Yes | ||
| consecutive_losses | Yes |
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?
Beyond the readOnlyHint annotation, the description adds valuable behavioral context: it is pure calculation, data-only, requires no HMAC, places no orders, has no wallet/account access, and is not trading advice. These details go well beyond what annotations already convey and give the agent a clear safety profile.
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 three concise sentences, front-loaded with the core purpose and return values, followed by safety/constraint details. There is no filler or repetition; every sentence earns its place.
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 pure-calculation tool with only two self-explanatory parameters and no output schema, the description is complete: it states the purpose, return values, input context, and all important safety/disclaimer caveats. The absence of an output schema is compensated by explicitly naming the return fields.
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 0%, so the description must compensate. The two parameters (consecutive_losses, recent_net_pnl) are self-explanatory and tied to the 'loss streak' context, but the description does not define their expected formats or bounds beyond the schema's min/max constraints. It adds some contextual meaning but not detailed parameter semantics.
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 provides advisory cooldown and size-penalty hints from a recent loss streak, listing exact return values (size_multiplier, cooldown_sec, severity). It distinguishes itself from sibling run_* tools by emphasizing that it is a pure, read-only, data-only calculation rather than an order or account operation.
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 usage after a recent loss streak and explicitly states read-only/no-order boundaries, but it does not provide explicit when-to-use/when-not-to-use guidance or name alternatives among the many sibling run_* tools. Context is clear but exclusions are only implied through safety constraints.
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 have clearly distinct purposes, and descriptions provide sufficient boundaries. Some run_* analytics tools (e.g., deflated_sharpe vs empyrical_metrics) could be conceptually confused, but their specific inputs and outputs minimize ambiguity.
All tools share the apex_ prefix, and the verb_noun pattern is consistent (get, query, run, submit). The 'agent_' subgroup within run tools introduces a minor irregularity, but it remains readily comprehensible.
With 24 tools, the server is on the heavy side, falling into the 16-25 range. Many run_* tools are similar in nature (pure calculations), but each appears to serve a specific purpose, so the count is borderline rather than excessive.
The server name implies a card store, yet the tool surface only supports reading and querying cards, with no create, update, or delete operations. This is a significant gap that prevents full lifecycle management, though the analytics side is fairly comprehensive.