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

With no annotations, the description carries the transparency burden. It discloses a key limitation (volume is not available) and explains the ranking metric (average bar range). However, it does not mention the output structure, possible side effects, or confirm that it is read-only.

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, the first clearly states the core behavior, the second frames the use cases. No redundant words, front-loaded with the most important 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?

Provides moderate context for a moderately complex aggregation tool, but lacks return structure details (e.g., whether it returns a list, what fields are included). Since there is no output schema, the description should clarify the output shape to be more complete.

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 only 50%, covering groupBy and timezone. The description adds the concept of a 'window' and references the grouping dimensions, but it does not explain to, from, timeframe, or instrument. At this coverage level, the description should compensate more, yet it adds minimal parameter-specific meaning.

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?

Directly states it groups bars by time unit (hour, day of week, month, year) and reports their movement. The explicit questions it answers ("which hour is actually worth trading", "is Monday different") clearly distinguish it from sibling tools like fxa_candles or fxa_session_scan.

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?

Implies usage for time-based pattern analysis by stating it answers specific trading questions in one call. It gives clear context on when to use, but does not explicitly mention alternatives or when not to use this tool.

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 provided, the description carries the full burden of behavioral disclosure. It adds valuable details beyond the schema: higher timeframes are aggregated from M1 on true clock boundaries, and it returns the most recent bars when the range exceeds the limit. This gives the agent realistic expectations about data generation and edge-case behavior.

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 sentences with no wasted words. It front-loads the core purpose in the first sentence, then adds two concise, high-value behavioral notes. Every sentence earns its place and the structure is easy to scan.

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 tool's moderate complexity, the description covers the primary input space (instrument, date range, timeframe), key behavioral rules (aggregation and limit overflow), and the expected output concept (OHLC candles). The absence of an output schema is partially mitigated by the 'OHLC candles' context. It could perhaps mention ordering or timezone, but it is reasonably complete for a fetch tool.

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 already documents all five parameters. The description adds some high-level context (e.g., 'over a date range', 'any timeframe from M1 to W1') but does not introduce new parameter-level details that are absent from the schema. It effectively reinforces, rather than expands on, 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?

The description clearly states the tool fetches OHLC candles for an instrument over a date range, with explicit timeframe support from M1 to W1. It uses a specific verb ('Fetch') and resource ('OHLC candles') that distinguishes it from sibling tools like fxa_level_touches or fxa_bucket_stats.

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 the primary use case (fetching candle data for an instrument over a time range) but does not explicitly state when to prefer this tool over alternatives or mention any exclusions. It provides useful context about aggregation and limit behavior but lacks direct comparative 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?

With no annotations, the description carries the burden. It discloses the result of pairing ('the trader can type or speak to you and you answer in their chart panel') and the code source, but does not mention permissions, failure modes, or connection lifecycle, leaving gaps.

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 concise sentences: first states the action and source, second explains consequence and trigger. Every sentence earns its place with no 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 connection tool with 2 params and no output schema, the description covers what it does, when to call, and the resulting state. It lacks explicit return/error info but is reasonably complete for the scenario.

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 baseline is 3. The description's example reinforces the 'code' parameter but adds no new meaning beyond the schema, and agentName is left as-is.

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 uses a specific verb ('Pair') and resource ('trader's open FXAbsolute chart'), and includes an example call. It clearly states the action and trigger, making it distinct from sibling tools like fxa_disconnect_chart.

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 when to call: 'Call this when the user gives you a pairing code' with a concrete example. It provides clear usage context but does not discuss exclusions or alternatives, so it stops short of a 5.

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 full responsibility for behavioral disclosure. It only states the action without explaining side effects (e.g., whether the remote peer is notified), whether it requires a prior connection, or what happens if called without an active session.

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 short sentence with no filler or redundancy. It conveys the essential purpose efficiently, which is ideal for a tool of this simplicity.

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 trivial zero-parameter disconnect operation, the description is mostly adequate but lacks behavioral context such as error conditions or whether the session is guaranteed to be released. It does not explain return values, though no output schema exists. Overall, it meets minimum viability but leaves room for improvement.

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 tool has zero parameters, so the baseline is 4. The description does not need to explain parameter meanings, and the empty schema fully covers this aspect.

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 uses a clear verb ('leave') and a specific resource ('paired chart session'), making the action unambiguous. It also naturally distinguishes from sibling tool fxa_connect_chart, as it is the inverse 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?

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites like an active session, nor does it name alternative tools for similar operations, leaving the agent to infer context.

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 transparency burden. It discloses a key data limitation ('this dataset has no volume') and implies a read-only operation through 'List', which is valuable behavioral context beyond 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?

The description is just two sentences: the first states the core purpose and output, the second adds usage guidance and a data caveat. Every sentence earns its place, with no 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 zero-parameter tool with no output schema, the description fully explains what the tool returns (instrument list with bar counts and pip size) and provides a notable data caveat. It is complete for an agent to decide when and how to use it.

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 tool has zero parameters, so the input schema is empty. The description doesn't need to explain parameters, and the baseline for zero-parameter tools is 4. The description's focus on output and data caveats is appropriate.

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 uses the specific verb 'List' and clearly identifies the resource ('every instrument FXAbsolute has candle data for') with output details (bar counts, pip size). This distinguishes it from sibling tools like fxa_candles, making its purpose unmistakable.

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 advises calling this tool first when unsure of available data, providing a clear usage context. It does not mention exclusions or alternatives, but the guidance is direct and actionable.

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 carries the full burden. It discloses the algorithm: finds touches, de-duplicates cluster, and measures reaction. This goes beyond a simple 'tests levels' and provides meaningful behavioral detail, though it omits output format specifics.

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?

Three concise sentences. The first sentence front-loads the core purpose, the second adds process detail, and the third uses a useful analogy. No unnecessary words.

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 8 parameters and no output schema, the description explains the concept well but lacks explicit return-value specification. 'Measures the reaction' is vague; the agent doesn't know what numeric output to expect. Time range parameters (from/to) are not addressed, leaving some completeness gaps.

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 63%, and the description adds context for key parameters: 'de-duplicates clustered touches' explains separationBars, and 'how close counts' relates to tolerancePips. It doesn't explain to/from but the schema already has no descriptions for those, so the description partially compensates.

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 function: 'Test whether a price level actually held' with a specific verb and resource. It also explains the process (finds touches, de-duplicates, measures reaction), making it distinct from siblings like candle retrieval or session scanning.

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?

Usage is implied ('when you want to test a price level') but no explicit alternatives or when-not scenarios are mentioned. The description doesn't contrast with sibling tools, so the agent must infer applicability from the purpose.

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 burden of disclosure. It provides useful context about the narrow side panel and the need for brevity, but omits potential side effects, prerequisites (e.g., whether a chart connection is required), or error behavior.

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 two sentences, front-loaded with the main action, and every clause adds meaning. It is concise and well-structured with no 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 tool with a single string parameter and no output schema, the description covers the essential aspects: purpose, destination, and formatting constraints. It could mention what happens after sending, but this is not critical for such a straightforward operation.

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 defines the 'text' parameter, but the description adds valuable guidance on the expected format (short and concrete) and the rendering context, which directly informs how the parameter should be populated.

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 sends a reply to the trader's chart panel. It uses the specific verb 'answer back' and identifies the destination, distinguishing it from sibling tools like fxa_connect_chart or fxa_wait_for_message.

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 the tool is for responding to the trader and explicitly instructs to keep the message short and concrete, with a note about the narrow panel. However, it does not explicitly mention when not to use it or name alternatives, though sibling context helps.

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 adds valuable behavioral context: session windows are evaluated in exchange-local time and daylight saving is handled, preventing hour shifts. However, it does not disclose return format or summary contents, which would be important for a summarizing tool, but the disclosed behavior is meaningful.

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 concise (three sentences) and well-structured: action, example, DST behavior, then alternative usage. Each sentence earns its place with no 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?

No output schema exists, and the description does not explain what the summary consists of or how includeRows affects output. This is a notable gap for a tool whose core purpose is summarization, though the example and parameter descriptions provide enough context for basic invocation.

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 88%, but the description enhances parameter understanding with a concrete example that clarifies relationships: 'bars [1]' means the opening bar, session 'nyse' is the cash session, and timeframe 'M5' is specified. This adds meaning beyond the schema's field descriptions.

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 verb 'Pull specific bars out of a trading session' and specifies the resource (trading session data) with a summarization output. It distinguishes from sibling fxa_candles by emphasizing summarization and pre-filtered session bars.

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?

It explicitly says 'Use this instead of pulling raw candles and filtering them yourself,' naming the alternative and giving clear guidance on when to prefer this tool. The example and DST/Exchange-local-time note further define appropriate usage conditions.

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 provided, the description carries the transparency burden. It discloses that the indicator is automatically cleared by fxa_reply, which is a useful behavioral trait beyond the raw toggle. It could specify whether on:false also clears the indicator, but the phrase 'Show or hide' implies both states.

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 sentences, each adding value: the action, the call pattern, and the clearing behavior. No filler 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?

The tool is a simple boolean setter with no output schema. The description covers its purpose, usage context, and interaction with fxa_reply, making it complete for an agent to select and call 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 0% (the 'on' property has no description in the schema), so the description must compensate. It gives a concrete example ('on:true') and the first sentence clarifies that true means show and false means hide, though not explicitly stated. For a single boolean parameter, this is adequate.

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 opens with 'Show or hide the thinking indicator in the trader's panel,' which precisely identifies the action and target. This clearly distinguishes it from sibling tools like fxa_candles or fxa_reply, none of which manage this indicator.

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 instructs to 'Call with on:true before a long lookup,' establishing a clear when-to-use scenario. It also mentions 'fxa_reply clears it automatically,' providing an interaction note with a sibling tool, though it does not explicitly enumerate exclusions.

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. It discloses blocking behavior ('Blocks until...'), timeout handling, and return semantics ('Returns waiting:false when nothing arrived'). It also explains the structured snapshot, which is a key behavioral outcome.

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?

Three concise sentences, each earning its place: the core action, the return value, and the recommended follow-up action. Front-loaded with the primary purpose, no fluff or repetition.

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 tool's simplicity (one parameter, no output schema), the description adequately covers all essential aspects: what it does, what it returns (text + snapshot, waiting flag), and how to handle the no-message case. No significant gaps remain.

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 input schema already fully documents timeoutSec with range and default ('How long to wait, 5–600 seconds. Default 240.'). The description adds no additional parameter-specific meaning, so the baseline score of 3 applies.

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 action: 'Wait for the trader's next message on the paired chart' with a specific verb and resource. It distinguishes itself from sibling tools like fxa_reply (sending) and fxa_connect_chart (connecting) by focusing on the waiting/blocking behavior.

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 useful context on how to use the result ('read that instead of asking them to describe what they are looking at') and instructs to 'call it again to keep listening' when waiting:false. Though it doesn't explicitly name alternatives, the sibling list makes the intended use clear.

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