Boolsai Signals

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

No annotations are provided, so the description must disclose behavioral traits. It explains the output (detected stack changes with week dates) but does not mention limitations such as data freshness, domain validity, rate limits, or error handling. This leaves the agent with incomplete expectations.

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 extremely concise: two sentences that directly state the tool's core function and a practical example. No extraneous information, and the key verb/task is front-loaded.

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 tool with 4 parameters, no output schema, and no annotations, the description adequately covers the main purpose and gives an example. However, it omits details on parameter defaults, pagination, and output format, which are needed for complete agent comprehension.

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 description adds meaning to 'domain' and 'contains' through the example, but does not explain 'limit' or fully describe 'change_type' (which includes 'changed' and 'any'). Schema description coverage is 50%, so it partially compensates but leaves gaps.

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 produces a week-by-week wayback diff timeline for one domain, returning stack changes with dates. It distinguishes itself from siblings by focusing on historical analysis, as exemplified by the specific use case of determining when a vendor was added or removed.

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 provides a concrete example of when to use the tool ('when did adobe.com add Segment?') and implies a historical context. However, it does not explicitly exclude cases when alternative tools like signal_diff or scan_at_date might be more appropriate.

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 carries burden. It implies a read operation by listing output data but doesn't explicitly state it's safe or side-effect-free. Adequate for inference but lacks explicit behavioral traits like read-only, idempotency, or auth needs.

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?

A single dense sentence packed with key outputs and usage context. Front-loaded with action and output summary. Slightly busy but no extraneous words, so earns a 4.

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 no output schema, description covers expected outputs thoroughly (diff, price action, alpha, wayback links). Sufficient for an agent to understand what the tool returns. Lacks details on response structure or error handling, but adequate for the tool's scope.

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% and the description doesn't add meaning beyond the schema's 'change_event id'. No elaboration on format or source for event_id, so baseline 3 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 clearly specifies the tool as a 'deep dive on a single event' and lists specific outputs (diff, price action, predicted vs actual alpha, wayback links). It distinguishes from siblings like 'find_signals' and 'recent_events' by indicating it investigates a specific event flagged by them.

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 use: 'investigate a specific event flagged by find_signals or recent_events'. This provides clear context and implies when not to use (e.g., for listing or comparing multiple events).

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 carries full burden. It discloses the process: 'Hits CDX → samples weekly → parallel-scans up to 50 snapshots via intel.boolsai.ai → inserts into wayback_intel_profiles,' and costs: '~30-60s wall time, ~50 intel scans.'

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 paragraph with logical flow: purpose, usage, process, post-farming action, cost. No unnecessary 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?

Despite no output schema, the description covers the entire workflow, prerequisites, and what happens after farming. It is complete for the tool's complexity.

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 descriptions for all 3 parameters. The description does not add extra semantics beyond the schema (e.g., default values, constraints) but mentions 'samples weekly' and 'parallel-scans up to 50 snapshots' which loosely relate to parameters.

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 starts with 'Bulk-farm a domain's historical wayback snapshots into our index,' clearly stating the verb 'farm', resource 'domain's historical wayback snapshots', and action. It distinguishes from siblings like wayback_backtest and domain_timeline by noting they are used after farming.

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 use: 'Use this when you need backtest history on a domain we haven't already farmed (i.e. wayback_backtest / domain_timeline return no data for it).' It also provides an alternative and post-usage action.

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?

Despite no annotations, the description conveys the tool is read-only (scans and returns results) and details the output (sorted by α at +7D descending) and filter capability (min_n). No destructive actions or authorization needs are implied, but the description adequately discloses the 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?

Three concise sentences with no waste: the first states the core purpose, the second gives usage guidance, and the third adds output ordering and filtering. The most critical info is front-loaded, making it easy to parse.

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?

With no output schema, the description sufficiently explains the return values (α, % positive, n) and sorting. However, it does not mention the top_k parameter that limits results, leaving a minor gap. Overall, it covers the essential aspects of the tool's behavior.

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 has 100% coverage with descriptions, but the description adds meaningful context: it explains that min_n sets a sample-size floor, that results are sorted by α at +7D, and that the output includes α, % positive, and n. This goes beyond what the schema alone provides, so above baseline.

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 performs automated pattern discovery by scanning specific combinations (event_type, detector, diff_field, severity) and returns those with strong forward-return characteristics (α vs SPY, % positive, n). It distinguishes itself from siblings like signal_diff or signal_landscape by targeting exploratory analysis when no specific hypothesis exists.

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 advises using the tool when you don't have a specific hypothesis yet, which provides clear context. However, it does not name specific alternative tools for hypothesis-driven analysis or explicitly state when not to use it, leaving some room for interpretation.

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 carries full burden. It discloses the return includes 'predicted α range' based on historical performance, but does not mention idempotency, rate limits, or whether it's read-only. The term 'Live signal feed' suggests real-time but is vague on update frequency.

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 plus a user-facing quote. Front-loaded with key idea 'Live signal feed'. No wasted 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?

For a simple tool with 2 optional params and no output schema, the description adequately explains what is returned (events with predicted α). Missing details on pagination or error handling, but these are not critical given the tool's 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?

Schema coverage is 100% with parameter descriptions. The description adds value by clarifying the 'min_co_occurrence' parameter with an example (4 = high-conviction) and reiterating the default for 'days'. This aids interpretation 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?

Description clearly states it returns recent events with predicted α range, using vivid language 'Live signal feed' and a concrete use case. Distinguishes from siblings like domain_timeline or event_dossier by focusing on temporal recency and prediction.

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 clear guidance: 'Use this to surface what should I be looking at right now?' This implies a monitoring/exploration context. No explicit when-not or alternatives, but the use case is well-defined.

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?

Describes the data transformation (wayback-wrapped URL) and return shape (same JSON shape as Boolsai Scan). No annotations exist, so description carries full burden; it adequately discloses the tool's read-only historical nature without omissions.

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?

Four sentences, each with a distinct purpose: purpose, backend mechanism, return format, usage advice. No redundancy, front-loaded with key action.

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?

Although output schema is absent, description notes the return shape, which is essential. It explains the tool's historical nature and use case. However, it could mention behavior when no snapshot exists or rate limits.

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?

Input schema has 100% coverage with clear descriptions for both parameters. Description adds minimal extra beyond restating 'YYYY-MM-DD' and 'original URL' already present in 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 the tool scans a historical URL via Wayback Machine using intel.boolsai.ai, distinguishing it from siblings like domain_timeline or wayback_backtest. The verb 'scan' and resource 'historical URL snapshot' are explicit.

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 specific usage scenario: 'Use when investigating WHEN a vendor was added/removed.' This gives clear context but does not explicitly exclude other cases or name alternatives.

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 details the return values (α, %pos, sample size, etc.) and notes 'Pure D1, fast', which gives performance insight. However, it doesn't explicitly state it's a read-only operation or mention side effects or auth needs.

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 efficient: two sentences plus a tagline. It front-loads the purpose, gives an example, lists outputs, and adds a performance note. 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 3 params, nested objects, and no output schema, the description provides good context: purpose, example, output summary, and speed. It relies on referencing test_filter for structure, which is acceptable if that tool is known. Minor gap: no explicit mention of sorting or limits.

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 67% with descriptions for signal_a and signal_b referencing test_filter args, but horizon_days lacks description. The description's example adds some context, but does not deeply explain the object structure 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?

The description clearly states the tool compares two signal patterns side-by-side, with a concrete example and outputs listed. It effectively distinguishes from siblings like find_signals (search) and test_filter (single filter).

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 through the example and mentions the input shape references test_filter, but does not explicitly state when to use vs alternatives or any exclusions. Usage context is present but not comprehensive.

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?

Discloses statelessness, pure D1 usage, caching behavior, and approximate response times, compensating for missing annotations by providing rich behavioral context.

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?

Concise paragraph with no wasted words, front-loading the core action and guidance, fitting essential information into a few sentences.

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, usage guidelines, and behavior well; lacks explicit return value description but the tool's nature (landscape) makes output somewhat self-evident; still slightly incomplete without output schema.

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 already covers all 5 parameters with descriptions (100% coverage), so the description adds minimal parameter-specific value beyond reinforcing the tool's overall purpose.

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 states a specific verb (computes) and resource (cross-signal sweep across multiple dimensions), clearly distinguishing from sibling find_signals by highlighting the one-shot nature.

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?

Explicit instruction to use this tool first before calling find_signals multiple times, with additional context on statelessness, no rate-limit risk, and fast response.

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 are provided, and the description does not disclose behavioral traits such as whether the tool is read-only, performance implications, or required permissions. For a tool with no annotations, the description should provide more transparency.

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, well-structured sentence with concise examples. No unnecessary words, and the core functionality and use case are front-loaded.

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 description explains the purpose and return values (n, mean/median returns, etc.), but lacks details on parameter interaction, limitations (e.g., date range size), or any prerequisites. Given the complexity of 7 optional parameters, more guidance would improve completeness.

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 has 100% parameter description coverage, and the description adds context by showing example filter expressions. However, it does not explain how the parameters combine into an 'arbitrary filter expression', which could be ambiguous.

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 computes alpha statistics for an arbitrary filter expression, with concrete examples like 'tier_count_changed on enterprise-SaaS tickers'. It distinguishes itself from sibling tools that likely focus on other analytical tasks.

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 the tool: 'test a specific hypothesis', and provides illustrative examples. However, it does not mention when not to use it or compare it to sibling 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 must fully disclose behavior. It indicates a read-like investigation ('investigate', 'show me everything we caught'), but it does not state if the tool is read-only, any side effects, rate limits, or data freshness. This lack of detail leaves agents guessing about operational traits.

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 at two sentences, front-loading the core purpose in the first sentence and a use case in the second. No fluff, but it could be slightly more informative without sacrificing conciseness.

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 (2 parameters, no output schema), the description covers the basic purpose. However, it lacks details about the 'price action timeline' format, pagination, or how it differs from siblings like 'domain_timeline' or 'event_dossier', which are also investigation tools.

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 description adds meaning for the ticker parameter by providing an example ('NFLX'), but it omits any explanation for the 'limit' parameter. Schema description coverage is 50%, and the description only partially compensates, leaving the agent without guidance on how limit affects results.

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 it retrieves 'all events fired on a single ticker, plus price action timeline' and provides a concrete example using NFLX. This distinguishes it from sibling tools by focusing on a single company's pattern, though it does not explicitly compare to alternatives.

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 advises to 'use this to investigate one company's pattern' and gives an example, implying its primary use case. However, it does not mention when not to use it or suggest alternatives among the sibling tools, leaving the agent without exclusion 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, but the description sufficiently explains the tool returns counts and summary data. It implies a read-only operation with no destructive side effects, meeting transparency needs.

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 covering purpose and usage without redundancy. Every word 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 no parameters or output schema, the description adequately covers the tool's role and return types. Could specify exact output structure, but the listed items (events, tickers, etc.) are sufficient for an overview 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?

The tool has no parameters, so the description doesn't need to add parameter meanings. Baseline of 4 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 clearly states the tool provides an overview of the research universe (events, tickers, date range, etc.) and explicitly says to call it FIRST, distinguishing it from sibling tools that drill into specifics.

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 explicit when-to-use guidance ('Call this FIRST when starting research') and explains the benefit ('let the agent reason about sample sizes before drilling in'), effectively guiding the agent.

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 are provided, so the description carries full burden. It describes the operation as a backtest but does not explicitly state it is read-only or disclose potential side effects, though none are expected.

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 sentences with no wasted words; the main action, benefit, and grouping options are all front-loaded and clear.

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 is provided, and the description does not mention return values or output structure, leaving the agent to infer what the backtest produces.

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 83%, and the description adds context for the 'since' parameter (default behavior) and lists grouping options, supplementing the schema definitions.

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 it runs an SPY-benchmarked backtest on the WAYBACK historical dataset, distinguishing it from a recent live dataset and specifying the dataset size and purpose.

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 suggests using this tool for backtesting with historical data for statistical confidence, implicitly contrasting with recent_events. However, it does not explicitly name alternative tools or state when not to use it.

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