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

Outstanding given no annotations. Discloses enforcement timing ('pre-execution'), specific error code ('402'), and user safety guarantee ('not a surprise bill'). Explains default read behavior when action omitted, critical for a tool with zero required parameters.

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, zero waste. Front-loaded with purpose, progresses through default behavior, mutation syntax, and enforcement guarantees. No repetition of schema details except where necessary for flow.

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 annotations and 100% schema coverage, description adequately compensates by explaining return behavior (current status) and error conditions (402). Absence of output schema is mitigated by explicit behavioral descriptions, though explicit return value structure for 'set' operation is implied rather than stated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, baseline is 3. Description adds value by explaining default behavior when action is omitted, and clarifying that 'set' action performs 'create/update' operations. Effectively links action and budget_usd parameters conceptually.

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?

Clear verb+resource ('Check or set your execution budget') but 'execution budget' terminology implicitly distinguishes from sibling 'check_balance' (likely account funds) without explicit comparison. Dual-mode nature (get/set) is immediately apparent.

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?

Excellent guidance on defaults ('Without action param, returns current status') and required parameter combinations ('Use action='set' with budget_usd'). Missing explicit distinction from 'check_balance' or when to prefer 'get_ledger', but covers the two primary usage patterns clearly.

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 fails to indicate whether this is a read-only operation, what data structure or format is returned (e.g., numeric value, currency object), or whether the balance is real-time versus cached. The term 'Check' implies reading but does not confirm safety characteristics.

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, efficient sentence with the action verb front-loaded. There is no redundant or wasteful text, and every word serves to clarify the tool's function.

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?

While adequate for a zero-parameter tool, the description is incomplete given the presence of multiple financially-related siblings (budget, get_ledger, spend, get_payment_url) and the lack of an output schema. It should clarify how this relates to other financial tools and hint at the return structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters, the baseline score applies per the rubric. The schema requires no additional semantic explanation, and the description correctly implies no user input is needed to retrieve the organization's balance.

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 ('Check') and identifies the resource ('current credit balance') and scope ('organization on Rhumb'). However, it does not explicitly differentiate from siblings like 'get_ledger' or 'budget' that may also return financial information, falling short of a 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 no guidance on when to use this tool versus alternatives such as 'get_ledger' (which may show transaction history), 'budget', or 'spend'. There are no prerequisites, conditions, or exclusion criteria mentioned.

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 adequately describes the three credential modes and what information is returned (availability status), but lacks explicit safety disclosure (read-only nature), rate limits, or side effects beyond the implicit non-destructive nature of 'Check' operations.

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 tightly constructed sentences with zero waste: action statement, explanatory detail of the three modes, and usage positioning. Information is front-loaded with the verb, and each sentence earns its place by conveying distinct information (what it does, what it shows, when to use it).

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 and the complexity of the three-mode credential system, the description successfully explains what the tool returns (availability across modes, BYO status). Minor gap: could briefly mention output format or example capability strings beyond the single 'email.send' example in the 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 coverage is 100% (baseline 3), but description adds valuable context by explaining the 'three modes' framework that the optional capability parameter filters against. This enriches understanding of what the parameter controls within the broader credential ecosystem.

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 verb 'Check' with clear resource 'credential status across all three modes', distinguishing it from siblings like 'credential_ceremony' (which performs provisioning) and 'execute_capability' (which runs capabilities). It explicitly defines the scope (Rhumb-managed, ceremony guides, BYO) that differentiates this discovery tool from mere capability listing.

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 positions the tool with 'Start here to understand what you can execute', providing clear sequencing guidance for the credential workflow. While it doesn't explicitly name alternatives to avoid, the 'Start here' directive effectively establishes prerequisites for using sibling tools like 'execute_capability' or 'credential_ceremony'.

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 dual return behaviors (list vs. detailed steps) and specifies what 'detailed steps' includes ('token format info, and documentation links'). Could improve by mentioning if results are cached or if the tool is idempotent, but solid disclosure of output content.

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, perfectly structured: 1) Core purpose, 2) Parameter-dependent behavior and return details, 3) Workflow usage guideline. No redundancy with schema. Every sentence earns its place with high information density.

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 discovery tool, coverage is strong. Compensates for missing output schema by describing return values ('detailed steps, token format info, documentation links'). Establishes relationship to 'agent_vault' in the ecosystem. Minor gap: could explicitly contrast with 'check_credentials' sibling, but sufficient given 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%, so baseline is 3. The description adds value by explaining the functional consequence of providing vs omitting the parameter (specific steps vs. list all), reinforcing the conditional logic. It adds semantic context about the examples (OpenAI, Stripe) indicating these are external service credentials.

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 ('Get') and resource ('step-by-step instructions for obtaining API credentials'). The name 'credential_ceremony' is jargon, but the description clarifies it means instructions for obtaining API credentials. It implicitly distinguishes from sibling 'check_credentials' (which verifies existing creds) by focusing on the acquisition process.

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 temporal guidance: 'Use this before agent_vault execute mode.' This establishes a clear workflow prerequisite. Also clearly documents the dual behavior: without service param it lists all ceremonies, with it returns specific steps.

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 compensates by disclosing return value structure ('provider counts and top provider info'), but omits other behavioral traits like auth requirements, rate limits, or side effects.

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 efficient sentences with zero waste. Front-loaded purpose ('Discover what capabilities are available') followed immediately by usage pattern and return value description.

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?

Adequate for a discovery tool with well-documented schema. Compensates for missing output_schema by describing return format. Minor gap: could note that all parameters are optional (required=0) to complete the contract.

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% ('Filter by capability domain', 'Search capabilities by text', etc.), establishing baseline 3. Description adds minimal semantic context beyond mapping 'domain or text' to the search functionality already documented 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?

Clear verb 'Discover' and resource 'capabilities' with explicit scope (search by domain or text). However, it does not distinguish from siblings like 'find_tools' or 'resolve_capability' which may overlap in functionality.

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 through 'search by domain or text' and indicates return data structure, but lacks explicit when-to-use guidance or comparison to alternatives like 'find_tools' or 'get_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?

No annotations provided, so description carries full burden. Discloses critical safety trait: 'without actually executing it' confirms read-only estimation. However, misses: return value structure (currency format? object?), cache behavior, validation scope (does it verify capability_id exists?), and whether estimates are binding or approximate.

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?

Optimal two-sentence structure: first sentence defines action and safety constraint; second provides usage context. No redundancy, tautology, or structural waste. Every word earns its place.

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 100% schema coverage and clear purpose, core definition is adequate. However, lacks output semantics (critical for an estimate tool): no description of return format (numeric? object? currency units?), precision guarantees, or error conditions. Since no output_schema exists, description should compensate for these 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 100% (all 3 parameters documented), establishing baseline 3. Description mentions 'capability' generically but doesn't augment parameter semantics beyond schema definitions—no clarifying examples, constraints, or inter-parameter relationships (e.g., when provider affects credential_mode).

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?

Excellent specificity: 'Get cost estimate for executing a capability' clearly defines the verb (get cost estimate), resource (capability), and distinguishes from sibling 'execute_capability' via 'without actually executing it.' Also differentiates from 'check_balance' (funds) and 'budget' (limit management).

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 temporal guidance: 'Use before expensive operations or when building cost-aware workflows.' Clearly signals intent for pre-flight cost checks. Lacks explicit 'when NOT to use' or named alternative comparisons (e.g., vs. 'execute_capability'), but context is clear enough for selection.

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. Discloses critical security behavior ('NEVER stored by Rhumb — used for this single request only'), auto-selection logic ('auto-selects the best healthy provider'), and fallback requirements ('Required to enable automatic fallback'). Missing operational details like rate limits or timeout 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?

Two dense sentences efficiently pack mode definitions and sibling references. Parenthetical explanations are effective, though the first sentence is information-dense. No wasted words; every clause adds specific parameter or mode requirements.

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 complex 9-parameter execution tool with credential management, covers execution modes, prerequisites, security implications, and provider selection. Adequate without output schema, though brief mention of error handling or response format would strengthen completeness further.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage (baseline 3). Description adds valuable cross-parameter logic: explains how credential_mode affects method/path requirement cardinality, specifies agent_token provenance (credential_ceremony), and adds security context not 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?

Clear specific verb ('Execute') + resource ('capability'), domain context ('through Rhumb'), and distinguishes from siblings by referencing resolve_capability (for discovery) and check_credentials (for validation) as prerequisite steps rather than execution.

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?

Excellent explicit guidance: defines three credential modes with specific requirements (byo requires method+path; rhumb_managed is zero-config; agent_vault requires agent_token from credential_ceremony). Directly references sibling tools for prerequisite steps and clearly maps parameter dependencies to modes.

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?

Mentions 'AN Score' ranking (behavioral trait), but lacks disclosure on read-only safety, rate limits, or what AN Score represents. Carries full burden since annotations are absent.

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?

Extremely efficient 7-word description. Front-loaded with action and scope. 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?

Simple 2-parameter tool, but lacks output description (no output schema provided). Could clarify search scope (all servers? current server?) and relationship to 'get_score' sibling given AN Score reference.

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% documenting both 'query' and 'limit'. Description doesn't add parameter-specific semantics beyond schema (e.g., query syntax tips, max limit rationale). Baseline 3 appropriate given schema completeness.

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?

Clear specific verb ('Semantic search'), resource ('agent tools'), and ranking criteria ('ranked by AN Score'). Compact but complete purpose statement.

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 on when to use this versus sibling 'discover_capabilities' or other discovery tools. No mention of prerequisites or when results are useful.

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

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

No annotations are provided, so the description must carry full behavioral disclosure. It mentions results are 'ranked' (ordering behavior) but fails to explain what 'AN Score' represents, what constitutes an 'alternative service', error handling (e.g., invalid slug), or whether results are paginated.

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 single sentence is front-loaded and efficient with no redundant words. However, the opaque 'AN Score' acronym detracts from clarity—without explanation, it creates ambiguity rather than 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?

For a single-parameter lookup tool with comprehensive schema coverage, the description is minimally adequate. However, the unexplained 'AN Score' metric and lack of output format description (textual or schema) leave gaps given the absence of annotations.

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%, with the 'slug' parameter adequately described as 'Service slug to find alternatives for'. The description does not add syntax details, format examples, or semantic constraints beyond the schema, meeting the baseline expectation.

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 (Find) and resource (alternative services), and specifies the ranking criteria (AN Score). However, it does not explicitly differentiate from sibling tools like 'get_score', and 'AN Score' is undefined jargon that may confuse the agent.

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 no guidance on when to use this tool versus alternatives such as 'get_score' or 'find_tools'. There are no stated prerequisites, conditions, or explicit exclusion criteria.

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, yet the description adds no behavioral context beyond the implied read operation ('Get'). It fails to disclose return format, whether results are cached, authentication requirements, or whether failure patterns include historical or theoretical data.

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?

Extremely concise at 6 words with verb-fronted structure. While efficient and waste-free, this brevity contributes to underspecification. However, the single sentence does earn its place by conveying the core operation.

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 and no annotations, the description should explain what failure patterns are returned and their structure. It also omits operational context needed for a retrieval tool (rate limits, data freshness). Incomplete for production use.

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% (slug is fully documented as 'Service slug to get failure modes for'). The description adds minimal semantic value beyond the schema, merely confirming the slug identifies a service rather than adding format constraints or examples.

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?

Clear verb ('Get') and resource ('failure patterns'/'failure modes') with scope ('for a service'). However, it does not explicitly differentiate from sibling tools like 'execute_capability' or 'discover_capabilities' which handle service operations rather than failure analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides no guidance on when to use this tool versus alternatives (e.g., when to query failure modes vs executing a capability), no prerequisites mentioned, and no exclusions or error conditions described.

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 disclosure burden. While it mentions 'recent' entries, it fails to define the time window, state whether the operation is read-only, describe return format, or mention pagination 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?

Single 7-word sentence is front-loaded with action verb and contains no wasteful language, though extreme brevity contributes to informational gaps.

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 omits return value documentation. However, the 100% schema-covered parameters and clear resource naming provide minimally viable context for this simple read 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?

Schema has 100% description coverage, documenting 'limit' (with default/max) and 'event_type' (with filter values). The description adds no parameter information, warranting the baseline score for high schema coverage.

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?

Uses specific verb 'Get' and identifies resource 'billing ledger entries' with organizational scope ('for your organization'). Lacks explicit differentiation from sibling 'check_balance', which also retrieves billing data.

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 no guidance on when to use this tool versus siblings like 'check_balance' or 'budget', nor does it mention prerequisites for accessing billing data.

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 disclosure burden. It identifies 'Stripe' as the payment processor and 'top up' as the transaction type, providing useful context. However, it doesn't clarify whether this creates server-side checkout state, idempotency concerns, or that it returns a redirect URL rather than processing payment immediately.

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 single sentence is perfectly sized with no wasted words. 'Stripe' and 'top up' provide essential context without verbosity. Information is front-loaded and structured for immediate comprehension.

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 (1 primitive parameter, no nested objects) and clear naming convention, the description provides sufficient context for invocation. However, without an output schema, it could explicitly confirm the return type is a URL string.

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%, documenting amount_usd thoroughly. The description mentions 'top up' which aligns semantically with the parameter purpose, but adds no syntax details, validation rationale, or usage examples beyond what the schema already provides. 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 uses specific verb 'Get' and identifies the resource 'Stripe checkout URL' clearly. It specifies the business purpose 'to top up Rhumb credits', distinguishing it from sibling tools like check_balance or budget which view credits rather than initiate purchases.

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 'top up Rhumb credits', suggesting it's for purchasing/adding funds. However, it lacks explicit when-to-use guidance comparing it to siblings like check_balance or budget, and doesn't state prerequisites (e.g., authentication requirements).

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?

Annotations are absent, requiring the description to carry full behavioral disclosure burden. While 'detailed' hints at data granularity, the description lacks information on read-only safety, caching, rate limits, authentication requirements, or error conditions.

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?

Extremely efficient seven-word sentence with strong front-loading (verb-first). No redundancy or filler content; every word serves the definitional purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a single-parameter lookup tool with complete schema documentation, though 'AN Score' jargon is unexplained and the lack of output schema means the return structure is only vaguely indicated ('detailed breakdown').

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 provides 100% coverage with 'slug' documented as 'Service slug to look up'. The description adds no parameter-specific guidance, meeting the baseline score for high-coverage schemas.

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?

Clear verb 'Get' and specific resource 'AN Score breakdown' identifies what the tool retrieves, though it doesn't explicitly differentiate from sibling 'get_' tools (get_alternatives, get_ledger, etc.) beyond implicit resource naming.

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 on when to use versus alternatives like get_alternatives or check_balance, no prerequisites mentioned, and no indication of when this lookup is appropriate versus other service-related 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?

No annotations provided, so description carries full burden. Discloses behavioral traits: returns ranked providers, health status, costs, and fallback chains. However, omits safety-critical context given financial siblings (budget, spend) exist—does not clarify if this operation is read-only, commits funds, or has side effects.

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, zero waste. First sentence defines function and output characteristics; second sentence front-loads the mental model for usage. Every word earns its place.

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 complex resolution tool with no output schema, the description adequately conveys what gets returned conceptually (rankings, costs, health, fallbacks). Slight gap: doesn't hint at return structure (object vs array) or integration with 'routing' sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with example values ('email.send', 'payment.charge'). Description reinforces the parameter through the example question but does not add syntax, format constraints, or enum semantics beyond what the schema provides. Baseline 3 appropriate for high schema coverage.

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?

Specific verb 'Resolve' with clear resource 'capability'. Distinguishes from siblings like 'execute_capability' (which runs the action) by emphasizing 'ranked providers with health-aware recommendations' and the decision frame 'what should I use?'.

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 implied usage context through the agent decision quote 'I need email.send — what should I use?', indicating it's for provider selection. However, lacks explicit guidance on when to use vs siblings like 'get_alternatives' or 'estimate_capability', or when to prefer 'execute_capability'.

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 disclosure burden. It successfully explains the behavioral logic of strategies (e.g., 'fastest' means healthiest circuits) and that quality_floor 'filters out low-quality providers', but omits safety characteristics, side effects of the 'set' operation, or potential error conditions.

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 dense, information-rich sentences with zero redundancy. The first sentence establishes the get/set dual purpose immediately and lists strategies; the second explains quality_floor. Every clause earns its place.

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 lack of output schema, the description should ideally disclose what values are returned on a 'get' operation or confirmation on 'set'. It also doesn't explain parameter interactions (e.g., does max_cost_per_call_usd only apply to 'cheapest'?). Adequate but with clear documentation gaps for a 4-parameter configuration 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 coverage is 100%, establishing a baseline of 3. The description adds significant semantic value by explaining what strategy values mean beyond the schema's simple list, and clarifies the purpose of quality_floor. It does not explicitly mention 'action' or 'max_cost_per_call_usd', preventing a score of 5.

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

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

The description clearly specifies the dual get/set operation on 'provider routing strategy' and enumerates specific strategy types (cheapest, fastest, etc.). While it doesn't explicitly contrast with sibling tools like 'budget' or 'check_balance', the specific domain ('routing strategy') distinguishes it sufficiently.

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 explains what each strategy means (e.g., 'cheapest (lowest cost above quality floor)'), which implicitly guides strategy selection. However, it lacks explicit guidance on when to use this tool versus siblings, prerequisites for calling it, or when to prefer 'get' versus 'set' operations.

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. Successfully discloses return structure (total spend, execution count, cost averages) and aggregation dimensions (capability, provider) compensating for missing output schema. Implies read-only operation through 'Get'/'Shows' verbs. Could add auth needs or rate limit notes.

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: action statement first, return value disclosure second (compensating for no output schema), default behavior third. 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?

Given single optional parameter, 100% schema coverage, and no output schema, the description adequately explains the conceptual data returned (metrics and grouping). Missing only minor details like pagination behavior or timezone handling for the period.

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 the 'period' parameter fully documented. Description repeats the default behavior ('Defaults to current month') but adds no additional semantic context about the date format or validation beyond what the schema provides. Baseline 3 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?

States specific verb 'Get' + resource 'spend breakdown' and scope dimensions 'by capability and provider'. The scope specification helps distinguish from siblings like 'budget' (limits), 'check_balance' (current credit), and 'get_ledger' (transaction log), though it does not explicitly name 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?

Provides implied usage through 'Defaults to current month', signaling when users might need to specify the 'period' parameter. However, lacks explicit guidance on when to use versus siblings like 'budget' or 'check_balance', or when to prefer over 'get_ledger'.

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