crypto-casinos

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

No annotations are provided, so the description carries the full burden. It clearly conveys that the tool returns decoded terms (not just raw data), and that expired promos are excluded. However, it does not disclose whether the tool makes any external API calls, its freshness/update frequency, or any latency implications. The description is adequate but not comprehensive for a tool with zero annotations.

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 relatively concise (2-3 sentences plus examples) and front-loads the core purpose. Every sentence provides value: the first defines what is returned, the second lists use cases, the third gives example JSON. No redundant fluff. However, the example call section could be slightly more structured, and the parenthetical warning about headline vs decoded terms, while useful, adds a bit of clutter.

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 has zero annotations, 2 parameters, and no output schema, the description covers the input semantics and use cases reasonably. However, it does not explain the output structure or data freshness (are bonuses cached/updated daily?). For a tool that decodes 'fine print', not detailing the response format or update cadence is a notable gap, especially with sibling tools like 'check_casino' that may have overlapping context.

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 50% (the 'casino' parameter has description while 'limit' does not in the schema). The description adds value by showing example values for both parameters ('limit': 5, 'casino': 'BetUS'), and explains the 'casino' parameter's purpose ('only bonuses from this casino'). For 'limit', it repeats the default behavior implied by the schema default of 10. This meets the baseline for 50% coverage but does not exceed it significantly.

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 a specific verb and resource: 'Current best crypto casino bonuses' with the 'fine print decoded' from T&Cs. It explicitly distinguishes what the tool provides (wagering requirement, max bonus, max cashout, real-value score) and what it excludes (expired promos, marketing headline). This clearly differentiates from siblings like 'top_casinos' or 'new_casinos' which focus on casinos themselves, not bonuses.

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 example call json snippets ('limit': 5 or 'casino': 'BetUS') which implies typical usage. It also lists example user queries ('best crypto casino bonus', 'deposit match with low wagering', 'is the X welcome bonus worth it?'), clearly defining when to invoke. However, it does not explicitly say when NOT to use this tool or name a specific sibling alternative for when to use those instead.

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 full burden. It discloses that data comes from hand-run real-money tests (not scraped), implying manual verification and no side effects. However, it does not mention error behavior for unknown casino names, rate limits, or authentication needs, leaving minor 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?

Description is efficient with four sentences that front-load the purpose, provide a concrete example output, and explain data provenance. Every sentence adds value without 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?

Given only one parameter and no output schema, the description adequately explains the return structure (trust score, audit status, live test details, etc.) with a sample call. It covers essential use cases but omits mention of error handling or edge cases for invalid names.

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 'name' has 100% schema description coverage, already explaining case-insensitivity and fuzzy matching. The tool description repeats these examples but adds no new semantic information beyond what the schema provides, meeting the baseline but not exceeding it.

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?

Clearly states the tool's core function: retrieving a forensic audit verdict for a single crypto casino, listing specific data points (trust score, audit status, live test details). Distinguishes from sibling tools which are for lists, comparisons, or bonuses, making the unique role obvious.

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 'Use for questions like ...' with concrete examples. Does not explicitly state when not to use or name alternatives, but the sibling list and the nature of the task provide implicit guidance. Clear context with no exclusion criteria, so a slight gap exists.

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 the full burden. It discloses that the tool compares casinos based on WagerX audit data and lists the specific fields (trust score, test, KYC, policy, withdrawal speed, license). The behavior is that it expects between 2 and 5 casino names and provides a side-by-side comparison. However, it does not specify what happens if a name is invalid (e.g., error vs. partial results), how up-to-date the data is, or whether results are returned in a specific format. This is a minor gap, but overall the description is quite 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 two sentences long with an example call appended. It front-loads the core action ('Compare 2-5 crypto casinos side by side') and immediately specifies the data source and fields. The second sentence gives real-world query examples, and the example call provides a concrete interface. Every sentence serves a purpose: defines scope, examples, and invocation. Zero 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?

Given that this is a straightforward comparison tool with 1 parameter, no output schema, and no annotations, the description covers the essential aspects: what it does, what data it compares, how many casinos, and an example call. It does not explain the output format or whether it returns a structured comparison vs. a textual answer. However, with siblings like 'check_casino' and 'list_casinos', the context is adequately set. The minimal input schema limits the need for more 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?

There is one parameter ('names') with 0% schema description coverage, so the description must compensate. The description explains that 'names' is an array of casino names (2-5), provides an example call, and adds context about what the comparison will cover. The schema only defines type, min/max items, and required status. The description adds meaning by specifying that these are crypto casinos and that the data comes from WagerX audit data. The example call also demonstrates expected values. A slight deduction for not explaining that the names must match some known identifier (e.g., exact internal name vs. generic query).

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 specific verbs ('Compare... side by side') and identifies the resource ('WagerX audit data') and the specific fields compared (trust score, test, KYC, withdrawal speed, license). It also distinguishes itself from siblings like 'check_casino' (likely single casino) and 'list_casinos' (listing, not comparing). The example queries ('Duelbits vs BC.Game?') and example call further clarify the tool's unique 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 explicitly states when to use this tool: to compare 2-5 casinos side by side, with concrete example queries ('Duelbits vs BC.Game?', 'Which is safer, Stake or Rollbit?'). It also defines the range (2-5 casinos) and provides an example JSON call, which guides the agent on how to invoke it. No mention of when not to use it or alternatives, but the sibling context (e.g., 'check_casino' for single casino) is implicitly clear.

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 clearly states that the lookup 'never executes remote tools' and enumerates the output categories, which is valuable behavioral context. It could additionally disclose whether the lookup is read-only or performs external network calls, but the current disclosure is solid.

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 tightly structured: it leads with the core action, lists return contents, gives concrete examples, and ends with a key safety property. Every sentence earns its place and there is no 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 single-parameter lookup tool with no output schema and no annotations, the description covers the essential context: what the tool searches, what it returns, example inputs, and a safety caveat. It is nearly complete; the only minor gap is how fuzzy or exact the matching behavior is, but examples largely cover that.

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 fully documents the single 'query' parameter. The description adds useful examples of query shapes but does not meaningfully expand on parameter semantics beyond what the schema provides; the 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 states a specific verb ('Look up') and a specific resource ('WagerX Agentic Gambling Index'), and enumerates exactly what the tool returns: endpoints, provenance, evidence status, access model, and limitations. It also gives concrete example queries, which strongly distinguishes it from the casino-focused sibling 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 explicitly says 'Use for questions such as...' and provides three representative query types. It does not explicitly name alternatives or give exclusion criteria, but the sibling tools are clearly casino-review related, so the intended domain is reasonably clear.

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?

The description discloses behavioral traits beyond the schema: determinism, aggregate-only statistics, and privacy guarantees (no raw queries, IPs, user agents, geography). With no annotations provided, the description carries the burden, and it covers several important constraints. It doesn't mention rate limits or caching, but for a stats tool the disclosed constraints are strong.

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, front-loaded with the core purpose and followed by important privacy/aggregation caveats. The caveats earn their place because they shape agent expectations. It could be slightly tighter but is appropriately sized.

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 read-only stats query with two enum parameters and no output schema. The description covers determinism, aggregate-only, provenance separation, and privacy. The main gap is lack of per-scope detail, but given the low complexity and the strong context provided, it is nearly 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 50%: the period parameter is documented as 'Used by activity statistics', but scope has only enum values with no descriptions. The description clarifies that activity counts are requests, not unique agents, which adds meaning to the activity scope, but it doesn't explain what each scope value returns. Baseline 3 is appropriate: the description helps somewhat but doesn't fully compensate for the undocumented scope semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names specific resources (WagerX Agentic Index, MCP/A2A endpoint observations, machine requests) and a verb (Return statistics). It distinguishes itself from casino-focused siblings by focusing on agentic statistics. However, it doesn't explicitly name a sibling alternative, so it misses the top tier for differentiation.

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 context: it is for deterministic aggregate statistics and explicitly contrasts with 'official provenance, editorial status and endpoint health' which remain separate. This signals when NOT to use it for authoritative data. However, it doesn't explicitly name sibling tools or lay out alternative conditions, so it falls 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?

No annotations are provided, so the description carries the full burden. It clarifies that the audits are 'real-money' and include real amounts, which adds some transparency, but it does not explicitly state side effects, read-only status, rate limits, or other behavioral details. The list nature is implied rather than stated.

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 plus a compact example. Every element earns its place: the action, the data details, the example queries, and the sample call. No filler 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?

Despite having no output schema, the description enumerates what each audit contains (deposit/withdrawal amounts, payout timing, support response), giving the agent a clear expectation of the return value. The single parameter is well-scoped by the schema, and the description effectively covers the tool's purpose and 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 description coverage is 0%, so the description must compensate. It includes an example call with limit=5, suggesting the parameter controls the number of audits, but it does not explicitly define the parameter's meaning. The schema already provides min/max/default, so the example adds some semantic value 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 opens with a specific verb ('List') and resource ('most recent WagerX real-money casino audits'), includes ordering ('newest first'), and details the content (deposit/withdrawal amounts, payout timing, support response). This clearly distinguishes it from sibling tools like best_bonuses or list_casinos.

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 natural-language queries for when to use the tool ('What are the latest casino audits?', 'Which casinos were tested this week?', 'freshest crypto casino safety data'). This gives clear usage context, though it does not explicitly contrast with alternatives 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.

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the tool lists casinos with trust score and audit status and takes no arguments. It does not mention authentication, rate limits, read-only nature, sorting, pagination, or any side effects. This leaves significant gaps for an agent to understand the tool's 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 that front-load the core purpose, then provide usage guidance. Every sentence is necessary and no words are wasted. It is appropriately sized for a simple listing tool.

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 list tool with no parameters, the description covers the basic 'what' and 'why to use it'. However, it lacks details on output ordering or sorting, and does not explain how this tool relates to sibling tools like top_casinos or new_casinos. Given the existence of these siblings, more context 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 tool has zero parameters and schema description coverage is trivially 100%. The description adds value by explicitly stating 'Takes no arguments.' For a zero-parameter tool, the baseline is 4, and the description meets it without needing further elaboration.

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 lists all casinos with audit data, including trust score and audit status. It uses a specific verb ('list') and resource ('casinos WagerX holds forensic audit data on'). While it mentions check_casino as a follow-up, it does not explicitly differentiate from siblings like compare_casinos or top_casinos, so it scores 4 rather than 5.

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 explicit use cases: 'Use to discover coverage before calling check_casino, or for "which casinos does WagerX cover?"'. This gives clear context for when to invoke the tool. However, it does not specify when not to use it or mention alternatives among siblings, preventing a score of 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 the full behavioral disclosure burden. It transparently reveals the sorting logic, the inclusion of audit evidence and caveats, and disclaims that this is not a safety ranking. However, it does not mention whether the list is exhaustive, how current the audit evidence is, or what the output structure looks like, leaving a minor transparency gap.

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 compact and front-loaded: purpose first, then a clarifying disclaimer, then usage queries, then the argument confirmation. Every sentence adds value and none are redundant with the schema or annotations. It is concise without losing essential 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 zero-parameter list tool with no output schema, the description covers all necessary operational knowledge: what is listed, the ordering, what data accompanies each entry, a caveat on interpretation, and usage scenarios. The only minor omission is the exact return format, but that is not critical given the tool's simplicity and the clear description of content.

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 reinforces this by stating 'Takes no arguments,' which prevents agents from inventing filter parameters. Nothing further is needed since there is no schema to supplement.

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 a specific verb and resource: 'List crypto casino brands by documented launch year, oldest first.' It clearly differentiates itself from siblings by emphasizing 'operating history, not a safety ranking,' which prevents confusion with ranking-oriented tools like top_casinos or latest_audits. The inclusion of audit evidence and ownership caveats further specifies the exact scope.

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 states when to use the tool via example queries: 'oldest crypto casinos', 'established bitcoin casinos', or 'long-running gambling sites'. It also provides a clear exclusion: 'This is operating history, not a safety ranking,' guiding agents away from using it for safety assessments. This is a strong when/when-not pairing.

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 fully discloses a key behavioral trait: results include casinos mid-audit, clearly marked and unscored until withdrawal test completes. This goes beyond a simple 'get new casinos' and adds safety context for an AI agent.

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 zero waste: first identifies the resource, second adds behavioral nuance, third gives concrete query examples. Front-loaded and efficient.

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 list tool without output schema, the description covers purpose, usage, and the critical audit-status edge case. Given sibling differentiation and no missing info, it is 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?

Input schema has zero parameters; description confirms 'Takes no arguments.' This adds certainty and matches schema coverage perfectly (100%). No further parameter information needed.

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 'newest crypto casinos on the WagerX radar', including those mid-audit. This distinguishes it from siblings like list_casinos (general list), top_casinos (ranked), and latest_audits (audit results) by focusing on recency and pending audits.

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 usage examples are provided ('Use for...'), which define when to invoke the tool. However, no direct comparison or exclusion of sibling tools is given; the context clues are sufficient but not explicit.

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: it discloses registry-based jurisdiction resolution, exclusion of non-approved authority domains, explicit missing/unavailable states, and the research-not-legal-advice nature. It stops short of describing return format or rate limits, but the disclosed traits are substantive.

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?

Every sentence earns its place: main purpose, registry constraint, exclusion rule, return state, non-legal disclaimer, example, and alternative mode. The JSON example is compact and informative. No fluff 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 tool with two optional parameters and no output schema, the description covers the key aspects: what it returns, how jurisdictions resolve, what is excluded, global list behavior, and legal limitations. Minor gaps remain (e.g., exact response structure), but nothing that would prevent a correct call.

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 documents jurisdiction with an example, and description adds registry-resolution context. Limit has no schema description, and the description only implies it via the example and 'bounded global list'. With 50% schema coverage, the description only partially compensates for the undocumented limit parameter.

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, resource, and scope: 'Get gambling regulatory context for a jurisdiction plus recent source-linked enforcement records.' This clearly differentiates it from all sibling tools, which are about casino bonuses, audits, and comparisons—none overlap with regulatory intelligence.

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 context for when to use the tool: for a jurisdiction, with an example, and explains the global-list behavior when jurisdiction is omitted. It does not explicitly name alternatives or exclusions, but no sibling tool provides regulatory context, so the usage guidance is sufficient.

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 burden. It discloses that only casinos with completed real-money deposit/withdrawal tests are ranked, and mentions factors (payout speed, KYC, support, license). This gives good insight into the tool's filtering and ranking logic, though it omits data freshness or 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?

Three sentences: purpose with criteria, usage examples, and an example call. Every sentence is essential and front-loaded. No redundancy or fluff.

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 list tool with one parameter and no output schema, the description covers purpose, ranking criteria, and usage context. It lacks details about output format (e.g., fields returned) or ordering (presumably descending by trust score), which 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?

Schema coverage is 0% (no parameter description in the schema). The description provides an example call with {'limit': 10}, implying the parameter controls result count, but does not explicitly define 'limit' or its behavior (e.g., maximum, default). This adds modest value beyond the schema's min/max/default constraints.

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 ranks best crypto casinos by 'WagerX audit trust score' and lists specific criteria (payout speed, KYC, support, license). It distinguishes from sibling tools like 'list_casinos' (general list) and 'new_casinos' (recent additions) by focusing on a curated trust-based ranking.

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 provides query examples like 'best crypto casino 2026', 'safest bitcoin casino', which tell the agent when to invoke it. However, it does not mention when not to use it (e.g., for single casino details use 'check_casino') or alternative sibling tools for other use cases.

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