ARX MCP Server

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

With no annotations provided, the description carries the burden. It discloses authentication requirements and that funds go to the caller's account, but does not explain what a 'deposit intent' entails (e.g., whether it's synchronous, if it requires approval, or what the return value is).

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 with no unnecessary information. Every sentence adds value: the first explains the core action, the second provides authentication and ownership context.

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

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

Given no output schema or annotations, the description is adequate but incomplete. It lacks details on the return value (e.g., deposit intent ID) and whether the creation is immediate or requires further steps.

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% description coverage, so baseline is 3. The description does not add extra meaning beyond the schema's descriptions of 'rail' and 'amountUnits'.

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 'Create a deposit intent' and clearly identifies the resource 'Buyer account'. It distinguishes from sibling tools like arx_get_balance (read) and arx_execute (execute) by its unique funding action.

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 states that it requires a Bearer API key and funds the caller's own account. This provides clear context on when to use the tool, though it lacks explicit alternatives or when-not-to-use conditions.

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

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

No annotations are provided, so the description must carry the behavioral disclosure burden. It reveals authentication requirements and buyer identity handling but does not mention side effects, idempotency, or rate limits. This is adequate but minimal.

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, using two sentences to convey purpose and critical authentication guidance. No redundant or vague wording is present.

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 three parameters, no output schema, and no annotations, the description covers purpose and authentication but omits parameter behavior, return values, and side effects. It is adequate for a straightforward execution tool but not comprehensive.

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 no information about the three parameters beyond what the input schema provides. Although schema coverage is 67%, the description does not explain timeoutMs or how parameters interact, missing an opportunity to add value.

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 executes a resolved capability via the AXP dispatch protocol, which differentiates it from sibling tools like arx_resolve. It also specifies authentication requirements, reinforcing its 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 implies usage after arx_resolve but lacks explicit guidance on when to use or avoid this tool. No alternatives or exclusivity conditions are mentioned, leaving the agent to infer context from the sibling list.

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 authenticated identity derivation and dev override. No annotations exist, so description carries full burden. Could detail response format 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?

Three compact sentences, front-loaded with primary action. Every sentence adds information 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?

No output schema, but description omits return value format (e.g., currency, amount). Adequate for basic usage but incomplete for an agent needing 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?

Single parameter buyerId is documented in schema; description adds dev-only context and production behavior. Adds value beyond schema's basic description.

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 'Get Buyer account balance' – a specific verb and resource. Distinguishes from siblings like arx_create_deposit and other getters (market, node, provider).

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 mentions authentication requirement and dev mode override. Usage context is clear, but no explicit when-not or alternatives stated.

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 cover behavioral traits. It states that the tool returns a record with constraints and supply stats, implying a read operation with no side effects. However, it lacks details on data freshness, error conditions, or idempotency, which are important for a tool with no annotation support.

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 with two sentences. The first sentence states the purpose, and the second gives a critical usage note. No unnecessary words, perfectly 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?

Given a simple input of one string and no output schema, the description covers purpose and authentication context adequately. It could mention that the output is a full record, but the domain knowledge likely suffices. Overall, fairly complete for a retrieval 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% with a clear description of the 'capability' parameter. The tool description does not add additional meaning beyond the schema; it only restates 'protocol ID'. Baseline 3 is appropriate as the schema already does the heavy lifting.

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

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

The description clearly states the verb 'Get' and the resource 'full ACS capability record including constraints and current supply stats'. It distinguishes itself from sibling tools like arx_list_capabilities and arx_search_capabilities by indicating it returns a full record with additional details like supply stats.

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

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

The description provides a clear contextual note: 'PUBLIC: No authentication required.' This helps agents understand when to use this tool without authentication constraints. However, it does not explicitly differentiate from siblings 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 provided, so description carries burden. It mentions authentication requirement (Bearer API key) which is good, but does not explicitly state non-destructive nature or idempotency. The operation is implied read-only by 'get', but not confirmed.

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 clear sentences, no redundant words. Essential information 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?

Simple tool with one parameter, but no output schema or return value description. Agent might need to know what fields are in the response for correct handling. Missing details on status and result 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?

Schema already describes parameter with 100% coverage. Description adds value by providing example format 'e.g. 'exec:ABCD1234'' and context that ID comes from arx_execute, which aids understanding.

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 'Get status and result of an execution by ID', specific verb and resource. Sibling tools like arx_execute are clearly distinct, so no ambiguity.

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?

Implied usage after arx_execute since it requires an execution ID, but no explicit guidance on when to use this vs other tools, nor conditions where it should not be used.

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 adds the note 'PUBLIC: No authentication required', which is helpful. However, it does not disclose other behavioral traits like rate limits, error behavior for invalid capability, or idempotency.

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 clearly states purpose and output fields, second sentence adds authentication context. Highly concise and 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 simple one-parameter tool with no output schema, the description mentions output fields ('node count, price range, median latency') but does not specify their structure (e.g., whether price range is an object with min/max). The public note is helpful, but more detail on output format 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% coverage (description for 'capability' is 'Capability protocol ID'). The tool description adds the context that market statistics are returned, but does not add parameter-level meaning beyond the schema. Baseline of 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 a specific verb ('Get') and resource ('market statistics'), and enumerates the included data (node count, price range, median latency). It clearly distinguishes from siblings like 'arx_get_capability' which likely returns capability details.

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 states the tool is public and requires no authentication, but does not provide guidance on when to use this tool versus alternatives such as 'arx_get_reputation' or 'arx_search_capabilities'. No explicit when-not or alternative recommendations are given.

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. Description mentions public access but does not disclose other behaviors such as rate limits, error conditions, or whether the call is read-only. Minimal transparency beyond authentication status.

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 with front-loaded purpose. 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?

For a simple get tool with one parameter and no output schema, the description covers purpose, key return fields, and auth requirement. Slight lack of error behavior details, but adequate overall.

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 covers 100% of parameters with description of nodeId format. Description adds no extra meaning beyond schema, so baseline score of 3 applies.

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

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

Description clearly states verb 'Get', resource 'node details', and specific data items 'current capacity and latest quote'. Distinguishes itself from sibling getters by specifying the exact node resource.

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?

Implied usage from 'PUBLIC: No authentication required', but no explicit guidance on when to use this tool vs alternatives like arx_get_provider or arx_get_market.

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 adds a behavioral trait ('PUBLIC: No authentication required'), which is valuable since no annotations are provided. However, it does not disclose other behavioral aspects such as read-only nature, potential return volume, or any 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?

The description is extremely concise: two short sentences that convey purpose and a key behavioral trait. Every word earns its place, with no redundancy or unnecessary details.

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 a single parameter, no output schema, and minimal complexity, the description adequately covers its function (provider profile and node list) and access requirement (public). It could specify that the output is read-only, but overall it's sufficient.

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 a clear description for the only parameter ('providerId'). The description does not add further meaning beyond the schema, thus baseline score of 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 states the action ('Get provider profile and node list') and distinguishes it from siblings like 'arx_get_node', which focuses on a single node. The verb 'Get' and resource 'provider profile' are specific and unambiguous.

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

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

The description mentions that no authentication is required, which gives usage context, but it does not specify when to use this tool versus alternatives like 'arx_get_node' or 'arx_search_capabilities'. No explicit exclusions or guidelines for scenario 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 are provided, so the description carries the full burden. It discloses that no authentication is required and implies a read operation, but does not explicitly state that it is read-only or describe any side effects, rate limits, or data sources.

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 with two sentences, front-loading the action and key public access trait. Every word adds value, 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?

No output schema exists, and the description does not mention what is returned (e.g., reputation score, format). It also does not specify whether nodeId and providerId are mutually exclusive. Given the tool's simplicity, the description is adequate but incomplete for an agent to fully understand 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 coverage is 100% with descriptions for both parameters. The overall description adds general context ('for a node or provider') but does not provide additional parameter-specific semantics beyond what the schema already offers.

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

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

The description clearly states the verb 'Get' and the resource 'empirical reliability reputation for a node or provider'. It distinguishes from sibling tools like arx_get_node and arx_get_provider by focusing specifically on reputation.

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 mentions that no authentication is required, which is a usage condition, but does not provide explicit guidance on when to use this tool versus alternatives like arx_get_node or arx_get_provider. It also does not clarify when to use nodeId vs providerId.

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 carry the full burden. It discloses public access and the default exclusion of huge schemas, but does not explain rate limits, response format, or what 'canonical' means. The behavioral insight is partial but not complete.

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 and a note, immediately front-loading the purpose and key behavior. Every sentence adds value 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?

There is no output schema, so the description should hint at the return value. It mentions 'No huge schemas included by default' but does not describe the output structure or pagination. For a list tool with two optional parameters, the description provides adequate context but not complete for an agent to fully anticipate the response.

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% (one parameter has a description). The tool description adds no additional meaning beyond the schema; it does not explain the 'status' parameter's enum values or the 'namespace' parameter further. Given low coverage, description should compensate but does not.

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

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

The description clearly states the verb 'list' and the resource 'canonical ACS capabilities available on ARX'. It distinguishes itself from siblings by noting public access and exclusion of huge schemas, and contrasts with 'arx_get_capability' and 'arx_search_capabilities' in 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 'PUBLIC: No authentication required', indicating when to use this tool. It implies that for filtered/search capabilities, sibling 'arx_search_capabilities' should be used, but does not explicitly state when not to use this tool or provide direct 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?

The description notes the tool is deterministic and requires authentication, but beyond that it discloses no behavioral traits. With no annotations provided, the description should cover aspects like side effects, rate limits, or data freshness; it falls short.

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 (two sentences) and front-loaded with the core purpose. The second sentence adds necessary authentication context. No fluff, but the structure could be improved by separating usage guidelines from purpose.

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

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

Given 5 parameters including nested objects, no output schema, and no annotations, the description is incomplete. It does not explain the return format, what 'resolve' entails algorithmically, or prerequisites beyond authentication.

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 80%, with parameters well-described in the schema (e.g., capability with example, optimization with sum constraint). The description adds no extra parameter meaning beyond what the schema provides, 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 states the tool deterministically resolves a capability to a provider node and quote. It specifies the action and resource, and while it doesn't explicitly distinguish from siblings like arx_get_capability, the deterministic resolution purpose is distinct enough.

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 authentication context ('AUTHENTICATED BUYER: Requires Bearer API key'), indicating when it's appropriate to use (as an authenticated buyer). However, it does not mention when not to use it or suggest alternatives like arx_search_capabilities for non-deterministic queries.

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?

Description adds key behavioral traits: deterministic (no AI ranking) and public (no auth). However, it omits other aspects like result ordering, pagination behavior (only limit given), and whether results are sorted or exact. Given no annotations, the description provides moderate coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states purpose with search fields, second adds behavioral and authentication details. No redundant or unnecessary text.

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 2 parameters and no output schema, the description covers purpose, one parameter's domain, and key behavioral traits. Missing: when to use vs siblings, how limit affects results, and expected output format. Adequate but not fully comprehensive.

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 describes 'query' as 'Search by protocolId prefix, ticker, or namespace' (50% coverage). The description repeats this but adds no new meaning for 'limit', which lacks schema description. Tool description does not compensate 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?

The description uses specific verb 'Search' and resource 'ACS capabilities', listing searchable fields (protocolId, ticker, namespace). It distinguishes from siblings like 'arx_list_capabilities' and 'arx_get_capability' by emphasizing keyword-based search.

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 explicit guidance on when to use this tool versus sibling tools (e.g., list vs search). The description implies use for keyword queries but does not state when to avoid or prefer alternatives.

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