Axiom Relay

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds 'No commercial obligation' and 'Risk R2; PUBLIC' which are context signals but not behavioral details about what the tool does or what happens when invoked. It does not contradict the annotations, but it also does not add meaningful behavioral transparency beyond them.

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 short, but it is not front-loaded with useful information. The first sentence is vague and jargon-heavy. The second sentence ('No commercial obligation. Risk R2; PUBLIC.') is terse but adds little value for an agent deciding how to invoke the tool. It is concise but not effectively structured.

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 one undocumented nested parameter, no output schema, and a vague description, the definition is incomplete. An agent cannot determine what input to provide or what the tool will return. The annotations cover safety but not the core operational context needed to use the tool correctly.

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

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

Schema description coverage is 0%, so the description must compensate for the undocumented 'apiDescription' parameter. The description does not explain what 'apiDescription' should contain, its structure, or how it is used. The parameter is a nested object with no schema details, and the description provides no guidance, leaving the agent to guess.

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 says 'performs bounded first-agent work through the shared capability policy dispatcher' which is vague and jargon-heavy. It does not state a concrete verb+resource (e.g., 'diagnoses API issues' or 'analyzes an API description'). The title 'API Doctor' hints at diagnosis, but the description itself fails to specify what the tool actually does. It also does not distinguish it from siblings like get_axiom_capabilities or search_directory.

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

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

No guidance is given on when to use this tool versus alternatives. The phrase 'bounded first-agent work' is unclear and does not explain the intended use case. There is no mention of when not to use it or which sibling tool might be more appropriate.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds 'No commercial obligation' (likely meaning no payment required) and risk level 'R1; PUBLIC', which exceeds annotation coverage by providing context about access and risk. It does not contradict 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 short, but it spends words on vague phrases like 'bounded first-agent work' and 'shared capability policy dispatcher' that do not earn their place. It is not front-loaded with the most useful information; instead, it opens with abstract jargon before stating 'No commercial obligation' and risk level. It could be rewritten to be more direct.

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 apparent role as a general concierge for answering questions, the description lacks essential details: what type of questions it can handle, what responses look like (no output schema), any limitations on scope, and how it differs from sibling tools. The annotations cover safety, but the description does not provide enough context for correct invocation.

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

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

With 0% schema description coverage, the description must compensate, but it does not mention the 'question' parameter at all. The only clue is the parameter name itself, which implies it takes a question, but there is no description of the expected format, length limits, or how questions are processed. The schema provides minimal information, so the description fails to fill the gap.

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 vague, corporate jargon like 'bounded first-agent work' and 'shared capability policy dispatcher' without explaining what the tool actually does in concrete terms. It does not state a clear verb-resource pair, and the title 'Axiom Concierge Core' only reinforces the ambiguity. An agent cannot infer that it likely answers questions, despite the parameter named 'question'.

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 its siblings, such as find_paid_service or search_directory. It mentions 'No commercial obligation' and 'PUBLIC' but does not clarify that this is for general answering while siblings handle specific capabilities. The sibling names suggest alternatives, but no routing logic is 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?

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful context beyond those annotations: field-by-field comparison, no commercial obligation, and Risk R0/PUBLIC classification. No contradiction exists, though return behavior is not described.

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 short sentences with no filler. The primary behavior and constraints are front-loaded, and the additional risk/commercial context is compact and informative.

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 one-parameter, read-only comparison tool, the annotations cover the safety profile and the description covers scope and constraints. The main gap is lack of explicit output/return description, but no output schema exists and 'field by field' provides a reasonable expectation.

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 clarifies that the slugs refer to declared service contracts and constrains the count to 2-4, but it does not name the parameter or explain slug semantics beyond the schema's regex and min/max constraints. Partial compensation only.

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 action (compare field by field), an exact input range (two to four), and an explicit non-goal (no ranking score). This clearly distinguishes it from directory/search or ranking siblings.

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 makes clear the operation is for comparing 2-4 declared contracts without ranking, so its appropriate use is implied. However, it does not name alternatives or exclusion conditions, leaving usage guidance implicit rather than 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?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds non-structured value: results are not ranked by an opaque score, the search carries no commercial obligation, and the data/risk profile is R0/PUBLIC, giving the agent a fuller behavioral model than annotations alone.

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 short sentences, front-loaded with the core action and parameters, followed by safety and commercial context. Every clause earns its place and there is no filler or redundancy.

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

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

For a two-parameter, read-only search tool this is nearly complete: purpose, parameter semantics, risk, and commercial implications are covered. The lack of an output schema is not fatal because the description says what is being searched and does not promise hidden ranking, but the exact return shape is left implicit.

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 carry parameter meaning. It maps `query` to 'declared text' and `maxCandidatePrice` to an optional 'price ceiling', adding roles beyond the bare property names. It does not explain amount formatting or currency, but those are already constrained by the schema patterns.

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 ('Search'), a well-defined resource ('public service contracts'), and the two search axes ('declared text' and 'optional price ceiling'). This clearly differentiates it from sibling tools like search_directory or get_directory_entry, which target directory entries rather than service contracts.

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 domain is clearly bounded to public service contracts in the Axiom Bazaar, and the phrase 'without an opaque ranking score' indicates when this tool is preferable for transparent matching. It does not explicitly name alternative tools or exclusion cases, but the context is strong enough for correct tool 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety behavior. The description adds context about the nature of the data ('canonical, versioned') and purpose ('approved for public discovery'), which is useful but does not disclose additional behavioral traits like ordering, pagination, or output format. With annotations handling safety, the description adds moderate value.

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 brief (two sentences) and front-loads the primary purpose. No unnecessary words. The 'No commercial obligation. Risk R0; PUBLIC.' segment adds some context but might be considered tangential; still, it does not bloat the description. Overall, it is appropriately concise.

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 absence of an output schema and the lack of parameter explanation, the description is incomplete. It does not explain what a 'capability contract' is, what the returned list looks like, or how to use the filters. Additionally, it fails to clarify its relationship with the sibling 'get_axiom_capability'. While the annotation set covers safety, an agent would struggle to invoke this tool correctly without additional external knowledge.

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 explain the parameters, but it does not. The parameters 'kind' and 'riskClass' are enums, which provide some self-documentation, but the description gives no hint of their meaning or how they affect the result. An agent cannot infer whether 'kind' filters by service/platform or what riskClass ranges mean. This is a significant gap.

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: 'List the canonical, versioned capabilities approved for public discovery.' It identifies the resource (capabilities) and describes them as canonical and versioned. However, it does not differentiate itself from the sibling tool 'get_axiom_capability' (singular), which likely fetches a single capability. The additional note 'No commercial obligation. Risk R0; PUBLIC.' is somewhat ambiguous but does not detract from the core 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 provides no guidance on when to use this tool versus alternatives. It does not mention the sibling 'get_axiom_capability' for single-capability lookups, nor does it explain any prerequisites or exclusions. The only contextual hint is 'approved for public discovery,' which implies this is for public-facing capability listings, but no explicit when/when-not guidance is 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?

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't need to restate those. It adds 'No commercial obligation; Risk R0; PUBLIC', which is useful safety/access context, but doesn't describe behavior for missing IDs or response details. Overall it supplements annotations without contradicting them.

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: one action sentence plus two clarifying tags. It is front-loaded with the core operation and contains no filler. Every segment earns its place, and the structure makes the tool's purpose instantly scannable.

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 single-parameter read operation, the description covers the essentials: what it reads, how it is identified, and that it is safe/public/no-obligation. It does not detail return format or error behavior, but with no output schema and strong annotations, the missing pieces are minor. The only notable gap is lack of guidance on what to do if the contract doesn't exist.

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 carries the full burden for parameter meaning. 'By stable identifier' clarifies that the 'id' parameter is a stable identifier, which is more than the bare schema provides. However, it lacks format guidance, examples, or how to obtain such an identifier, leaving the agent with minimal practical guidance.

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 ('Read') with a clear resource ('canonical capability contract') and method ('by stable identifier'). The singular 'one' distinguishes it from the sibling 'get_axiom_capabilities', which likely lists contracts. The added context 'No commercial obligation; Risk R0; PUBLIC' makes the operation's nature unmistakable.

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

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

The description implies usage: use this tool when you have a stable identifier and need a single capability contract. However, it doesn't explicitly state when not to use it or point to alternatives such as get_axiom_capabilities for listing or find_paid_service for commercial discovery. 'No commercial obligation' hints at boundaries but doesn't direct the agent to siblings.

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 already establish read-only, idempotent, non-destructive behavior. The description adds useful context beyond these: the operation is 'PUBLIC,' has 'Risk R0,' and carries no commercial obligation, plus canonical single-entry semantics.

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 short sentences with no filler. The core action and identifier options are front-loaded, and the risk/public classification is appended compactly.

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 with strong safety annotations, the description is essentially complete: it states the input identifier types and the read-only nature. It does not specify return shape, but title implies a description and annotations cover safety.

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%, so the description carries the full burden for the 'entry' parameter. It compensates by explaining that the value may be a slug, capability id, or stable directory id, which is meaningful guidance the schema itself does not provide.

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 uses a specific verb ('Read') with a specific resource ('one canonical directory entry') and names three identifier types, making it distinct from sibling search tools like search_directory. It clearly states the tool's singular, canonical lookup 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?

Implied usage is clear: call this when you have a slug, capability id, or stable directory id and need the canonical entry. It does not explicitly name alternatives or state when not to use it, but the identifier-based, single-entry wording provides enough routing context.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds relevant access/risk context: 'Risk R0; PUBLIC' and 'No commercial obligation,' which go beyond the annotations and help the agent understand the operational context.

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

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

The description is concise and front-loaded with the action and resource. The extra clauses add some context, though 'truthful' is slightly redundant and could be removed without loss.

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 parameterless, read-only list tool, the description adequately conveys the returned content categories and access posture. There is no output schema, but the listed categories give enough expectation for a simple listing, though output shape is not detailed.

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 coverage is 100%, so there is nothing for the description to add semantically. The baseline of 4 for a parameterless tool 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 clear action ('List') and resource ('room contracts, participation policy, and transport availability'). It is specific enough to distinguish from siblings, none of which mention rooms, though the adjective 'truthful' is somewhat vague.

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?

There is no explicit guidance on when to use this tool versus alternatives like search_directory or get_directory_entry. The read-only listing nature implies a browse use case, but no exclusions or selection criteria are 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?

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds useful context beyond that: entries are 'projected from CapabilityContract and Merchant records,' are 'neutral,' and carry 'No commercial obligation. Risk R0; PUBLIC.' This enriches the behavioral profile without contradicting the 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 concise and front-loaded: the core action and resource appear first, followed by scope and risk in short, information-dense clauses. Every sentence earns its place, and there is no filler or repetition of the tool name/title.

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 high parameter count (15), no output schema, and zero parameter documentation, the description is not complete enough for correct invocation. It does not explain result shape, pagination, ranking-policy specifics, filter combination behavior, or how canonical/neutral entries are determined, leaving significant gaps for an agent.

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%, and the description only mentions 'explicit filters and ranking policy' without mapping any of the 15 parameters to specific behavior or explaining their semantics. Parameter names and enums are suggestive, but the description does not compensate for the complete absence of schema-level documentation.

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 action ('List'), a resource ('canonical Axiom Directory'), and a distinctive scope ('neutral directory entries projected from CapabilityContract and Merchant records'). This differentiates it from sibling get_directory_entry, which appears to fetch a single entry, and from compareServices or find_paid_service, which imply comparison or paid discovery.

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 explicit when-to-use guidance or comparison with alternatives. It implies a search/filter use case via 'explicit filters and ranking policy,' but it never states when to prefer search_directory over siblings like get_directory_entry, compareServices, or find_paid_service.

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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context about what is validated (MER envelope, canonical evidence links, Ed25519 proof) and the risk level (R1; PUBLIC), which goes beyond the annotations. It does not describe output format or failure behavior, but with no output schema and strong annotations, this is a moderate 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 two sentences with no wasted words. It front-loads the core action ('Validate the public MER envelope...') and adds the key context ('without trusting marketplace claims') and risk classification ('Risk R1; PUBLIC') efficiently.

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, read-only, idempotent tool with no output schema, the description covers the essential behavioral context: what is validated, the trust model, and the risk level. It does not describe the return value or error cases, but the absence of an output schema and the simplicity of the operation make this a minor gap.

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 0 parameters, so the schema provides no parameter documentation. The description compensates by explaining what the tool validates, which is the only relevant semantic context. With no parameters to document, a baseline of 4 is appropriate.

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

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

The description states a specific verb ('Validate') and resource ('public MER envelope, canonical evidence links, and sandbox Ed25519 proof'), which clearly identifies what the tool does. It does not explicitly distinguish itself from siblings, but the sibling names are unrelated enough that confusion is unlikely.

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 by mentioning 'without trusting marketplace claims' and 'No commercial obligation', which suggests when to use this tool (for verification independent of marketplace trust). However, it does not explicitly state when not to use it or name alternative tools for related verification tasks.

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