BitCLI — Crypto Futures & Order Flow

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

With no annotations, the description carries the full burden and does so: it discloses state mutation, that alerts fire out-of-band (Telegram/Discord) without the agent staying awake, per-action pricing ($0.001 vs $0.002 wildcard), balance requirements, TTL auto-expiry, and the shape of error payloads. This is exactly the behavioral context annotations would otherwise supply.

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?

Labeled sections (BEHAVIOR / PRICING / ACTIONS / USAGE / ERRORS) front-load the mutation and async semantics before the per-action breakdown. Every line conveys distinct information — no restatement of the name or filler prose.

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?

No output schema exists, and the description compensates by stating what `create` returns (alert_id plus expiration) and what `list` returns (active triggers, IDs, remaining TTLs). Combined with auth, pricing, capacity, and error behavior, an agent has everything needed to invoke this five-parameter mutation tool correctly.

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 coverage is 100%, so the baseline is 3, but the description goes further by mapping parameters to actions — 'create' requires `command`, 'cancel' requires `alert_id`, and 'list'/'clear_all' explicitly ignore them. That action-parameter interaction is not expressed anywhere in the schema and prevents misfires; only the `destinations` and `ttl_minutes` routing details are left entirely to the 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?

States a specific verb family (inject/remove triggers) and resource (in-memory execution triggers in the C++ engine), then enumerates the four concrete actions with what each does. An agent can immediately tell this apart from `market_data` polling and `calc_engine`.

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?

Explicitly routes the agent: 'Use this tool to establish asynchronous monitoring instead of polling `market_data`.' It also states the prerequisites (authenticated API key, guests get an auth error) and the constraint (plan capacity limits), so when-to-use and when-it-will-fail are both covered.

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

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

With no annotations, the description carries the full burden and does so: it declares determinism, states the per-execution price and the billing source (daily quota or USD balance), and specifies the error contract ('Malformed syntax returns an error JSON key with correction guidance'). Those are exactly the non-obvious behaviors an agent needs before calling a metered tool.

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?

Labeled sections (BEHAVIOR, PRICING, SYNTAX, RETURNS, USAGE, ERRORS) put the essential framing first and are scannable. The six example commands are individually informative but collectively borderline verbose; trimming to four plus a note on grammar would lose nothing.

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?

There is no output schema, so the description steps in with the concrete return keys ('ideal_lot_coins', 'liquidation_price', 'effective_rr_ratio', etc.), plus error and pricing behavior. For a two-parameter, metered, DSL-driven tool, nothing an agent needs in order to invoke it correctly is missing.

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 coverage is 100%, so the baseline is 3; the description earns above that by supplying six worked command strings covering position sizing, liquidation, DCA, R:R, carry cost and ATR stops, which convey the DSL grammar that the schema alone only gestures at with one example. It does not fully formalize argument order or units, keeping it short of a 5.

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?

States a specific verb and resource ('deterministic mathematical calculation' of crypto futures risk management models) and immediately scopes out live data by naming which sibling handles it. The command examples make the resource concrete enough that an agent knows exactly what class of work belongs here.

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?

Explicitly routes work: 'use this tool exclusively for mathematical risk modeling and lot sizing', 'for live market scanning, use market_data', 'for setting execution triggers, use alert_manager'. It also gives a proactive follow-up ('route the generated stop-loss or liquidation prices into alert_manager'), which is rare and useful.

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

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

With no annotations present the description carries the entire burden and does so unusually well: it declares read-only behavior, a per-execution price ($0.001) with the billing source (daily tariff quota or USD balance), and a precise error contract (JSON error object with syntax correction guidance). Those are the cost and failure-mode facts an agent cannot get from the schema.

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?

Front-loaded and sectioned (BEHAVIOR / PRICING / ACTIONS & RETURNS / USAGE / ERRORS), so the read-only and cost facts appear before the detail. Every block carries information an agent needs given there is no output schema; nothing is redundant filler.

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 9-parameter, 3-mode tool with no output schema and no annotations, the description compensates fully: it explains each action's return fields, the cost model, the error format, and the polling anti-pattern. An agent can select an action and interpret the response without further documentation.

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 coverage is 100%, so the baseline is 3; the description adds value by tying each action value to its output shape (screener's symbol/rvol/fund/oi field list, consensus's TA score set, bct_matrix's compact matrices) and by flagging that malformed filter expressions fail with corrective guidance. It does not add syntax detail for tf, limit, columns, exchange, or inline_indicators beyond the 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?

Opens with a specific verb+resource ("fetches real-time derivatives intelligence across Binance, Bybit, and Hyperliquid") and then enumerates all three actions with what each returns, so an agent knows exactly which mode to request. It also separates itself from the sibling alert_manager by name.

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?

Gives an explicit positive case ("analyze market state or find trade setups") and an explicit exclusion ("Do NOT use this tool to continuously poll for price updates or wait for conditions") plus the named alternative (alert_manager). That is the full when/when-not/alternative triad.

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

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

No annotations exist, so the description must carry the full burden, and it does: per-dispatch cost ($0.001) and quota/balance deduction, authentication and destination-ownership requirements, error conditions (unverified/foreign destinations, empty messages, exhausted quotas), and the JSON return payload. These are operational traits an agent cannot infer from the schema.

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?

Labelled sections (BEHAVIOR, PRICING, PARAMETER INTERACTIONS, RETURNS, USAGE GUIDELINES, ERRORS) front-load the purpose before details. Slightly verbose in places — the RETURNS block partly duplicates what a caller would get anyway — but nearly every line carries actionable information.

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 3-parameter side-effecting messaging tool with no annotations and no output schema, the description supplies everything needed: cost model, auth preconditions, destination format, transport-specific formatting, error surfaces, and return shape. Nothing material is left implicit.

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 coverage is 100%, so the baseline is 3; the description earns above that by explaining the target prefix grammar ('tg_user:'/'tg_channel:'/'out_wh:') and how 'title' and 'message' render differently per transport (Discord embed headline/description vs. Telegram bold header/HTML body). These behavioral mappings are only partially present in the 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?

States a specific verb and resource ('Outbound messaging operation ... routes proactive notifications to the human trader's verified Telegram chat, channel, or Discord webhook') and enumerates the message classes it carries. It is clearly distinguishable from alert_manager (triggers/monitoring) and user_account (destination discovery).

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?

Explicitly says to call `user_account` with action='list_destinations' before sending, restricts the tool to informative messaging and human-in-the-loop updates, and names the alternative ('Do NOT use this tool to monitor market prices or set execution triggers (use `alert_manager` instead)'). Both when-to-use and when-not-to-use are covered.

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

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

With no annotations, the description carries the full burden and does so well: it declares read-only behavior, zero cost/no quota consumption, the exact return shape (single Markdown string), and the error contract for an invalid topic. What's missing is any hint of document size or retrieval latency, so it stops just short of fully describing the experience.

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?

Sectioned as BEHAVIOR / PRICING / USAGE / TOPICS / ERRORS with the core purpose front-loaded, so an agent can skim. The TOPICS list and PRICING block add bulk, but each entry maps to a real decision the caller must make, so little is pure filler.

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 one-parameter lookup tool with no output schema, the description covers purpose, exclusions, valid values with meaning, cost, return type, and failure mode. An agent has everything needed to invoke it correctly on the first try.

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 coverage is already 100% with an enum, so the baseline would be 3; the description earns above that by glossing each topic value (e.g. 'calculators' = position sizing, true MMR liquidation, DCA break-even), which lets an agent pick a chapter without guessing from the label alone. The glosses are brief and the labels are largely self-descriptive, keeping it off a 5.

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?

States a specific verb and resource: reads and returns official BitCLI markdown specifications for formulas, CLI guides, and webhook setups. The read-only RAG framing plus the return type (a single Markdown document string) makes it unambiguous and clearly distinct from siblings like market_data or alert_manager.

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?

Explicitly says to use this tool FIRST to learn BitCLI mechanics or verify command grammar, and explicitly excludes live price/active-trigger queries by naming the alternatives (market_data, alert_manager). Both the when and the when-not are stated with the substitute tools.

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

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

With no annotations, the description carries the full burden and does well: declares read-only behavior, zero cost and no quota/balance consumption, and the 401 failure mode for missing API keys. It stops short of rate limits, pagination, or whether list_destinations results can go stale — minor gaps for a query tool.

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?

Labeled sections (BEHAVIOR, PRICING, ACTIONS, USAGE GUIDELINES, ERRORS) make it scannable and the scoping information is front-loaded. Slightly verbose — the pricing line could be folded in — but nearly every line carries actionable content.

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?

There is no output schema and no annotations, yet the description compensates by listing the return fields per action, the cost model, the auth requirement, and the error behavior. An agent has everything needed to call this correctly.

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 coverage is 100% with a two-value enum, so the baseline is 3; the description adds real value by documenting what each enum value returns (billing fields vs. dispatch targets) and how list_destinations feeds into alert_manager. It does not constrain format or selection criteria beyond that.

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 states precisely what the tool does — a read-only query of ledger states, subscription tiers, and verified notification endpoints — and enumerates the two concrete actions with their return contents. It also names what it is not (alert_manager, market_data), so an agent can distinguish it from siblings without opening the schema.

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?

Explicitly prescribes timing ("Use this tool at the beginning of a workflow to understand available budget and determine valid delivery destinations") and gives two explicit exclusions with the correct alternative named for each. Nothing is left to inference.

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