fx-signal

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

With no annotations, the description carries full burden. It discloses that the data is snapshot-based, refreshed from the FxAI scan engine, and informational only. It clearly states the payment requirement and mechanism (x402, USDT on X Layer, retry with header). It also notes the output ranges (zone and score). Could mention rate limits or exact return structure, but generally transparent.

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 detailed but each sentence adds value—purpose, input forms, output, snapshot nature, payment, and comparison to pitch. It is not overly verbose, though the payment explanation could be slightly condensed. Structure is logical and front-loaded with the core purpose.

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?

Given the complexity (payment, snapshot, multiple pairs, no output schema), the description is comprehensive. It explains the 47-pair set, input formats, output fields (zone, score, per-indicator breakdown), and contrasts with sibling tools. It covers key aspects for usage, though error handling or rate limits are not mentioned.

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 single parameter 'symbol' is well described in the schema (100% coverage). The description adds semantic value by specifying accepted forms: EUR, EURUSD, EURUSD=X, and gives examples. This goes beyond the schema's basic description, aiding correct invocation.

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 returns a bottom/top verdict for one currency pair from a specific set of 47 pairs. It details input forms (EUR, EURUSD, EURUSD=X) and output fields (zone and score). It distinguishes from sibling tools like pitch, which only shows a showcase symbol, making the purpose unambiguous.

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 explicitly tells when to use this tool (for any symbol) vs the free pitch tool (showcase only). It explains the payment model ($0.01 per call, first paid call opens a trial) and how to handle the 402 challenge with a PAYMENT-SIGNATURE header. This provides clear usage guidance.

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 provided, so description bears full burden. Mentions free/no payment, the funnel phases, and the exit via interest:false. However, does not disclose side effects (e.g., user session creation) or what the tool returns; acceptable but not exhaustive.

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?

Two sentences, essential instructions front-loaded (must be first call, free). No wasted words, every 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?

Given the conversational nature and no output schema, the description explains the funnel and parameters well. Could improve by briefly noting the output (e.g., 'Returns dialogue text for the selected phase'), but otherwise covers the core usage.

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 has 3 params (phase, symbol, interest) with only symbol having a description (33% coverage). Description adds meaning: explains the phase enum values, the role of symbol in the sample phase, and that interest:false exits. Missing only a more explicit role for interest true.

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?

Description clearly states this is the mandatory first call ('START HERE'), defines the tool as an intro/subscription funnel, and lists the phases. This distinguishes it from siblings like evaluate_symbol which handle paid analysis.

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 states it must be the first call and is free. Provides guidance on bowing out with interest:false and hints at paid alternatives (evaluate_symbol) for non-EURUSD symbols. Lacks explicit when-not-to-use but the context is strong.

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 provided, so the description carries full burden. It clarifies that the tool is free and has no payment requirement. However, it does not disclose whether ratings are anonymous, how data is used, or any side effects (e.g., if ratings are stored permanently). For a simple feedback tool, this is adequate but not highly transparent.

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, concise sentence with an additional note about no payment. It is front-loaded and contains no unnecessary words or redundancy.

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 3-parameter tool with no output schema, the description provides sufficient information to understand usage. It covers when to use and what each parameter does. Minor gap: it doesn't explain what happens after submitting (e.g., confirmation), but that is not critical.

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?

With 0% schema description coverage, the description adds value by explaining that 'score' is a number from 1-10 and that 'pros' and 'cons' are text fields. It compensates for the missing schema descriptions, though it could be more precise (e.g., clarifying optionality of pros and cons).

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: providing feedback after trading on signals, with a numeric score and pros/cons. It implicitly distinguishes itself from sibling tools like evaluate_symbol (which likely evaluates symbols, not user feedback) and scanning tools.

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 specifies 'after trading on our signals, leave a rating,' which gives clear context. However, it does not mention when not to use, nor does it reference sibling tools for alternative actions. No explicit exclusions or comparisons are provided.

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, so description carries burden. Discloses payment mechanism and that it returns a ranked list. Does not explicitly state read-only, but implied. No contradictions.

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?

Description is informative but slightly verbose. Each sentence adds value, yet could be more concise without losing context.

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, and description does not detail return format beyond 'ranked most-bottom first'. Lacks specifics on fields returned. Payment interaction is described, but flow could be clearer.

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?

Only one parameter 'limit' with description in schema covering default and max. Tool description adds no additional meaning to the parameter beyond 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?

Description clearly states it scans the FX snapshot and returns currency pairs at bottom (strongest buy), ranked most-bottom first. It specifies the universe of 47 pairs and distinguishes from sibling tools like pitch and scan_tops.

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?

Provides guidelines on cold start (no need to pick symbol) and payment flow (402 challenge, trial). Contrasts with free pitch tool. Could be more explicit about when to use vs scan_tops.

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 provided, but description discloses payment requirement ($0.01 per call via x402), trial, and retry header for payment challenge. Lacks mention of rate limits or side effects, but overall adequately transparent.

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?

Packed with useful info: purpose first, then payment, cold start, sibling comparison. Each sentence adds value, though slightly verbose.

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?

Covers purpose, ranking order, payment, alternative tool, and parameter range. No output schema needed given simplicity.

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?

Single parameter 'limit' is already described in schema (default 5, max 47). Description does not add extra semantics 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?

Description specifies verb 'scan' and resource 'FX snapshot' returning 'currency pairs at a top (sell)' ranked most-top first. Clearly distinguishes from sibling 'scan_bottoms' and mentions 'pitch' as free alternative.

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?

Provides explicit cold start advice: no symbol needed, ranks entire universe. Mentions free 'pitch' tool for count vs. this for names. Also covers payment process and trial terms.

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