agent-verified-relay

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

With no annotations provided, the description bears full burden. It reveals behavioral traits: idempotent (replay returns original receipt), failure handling (receipted evidence, not silence), and notarization process (request hash + response hash + outcome). It does not cover auth needs or rate limits, but the disclosed traits are substantial and accurate.

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

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

The description is concise at two sentences. The first sentence is dense but front-loads the main purpose. Every sentence adds value: first states primary function, second explains idempotency and failure behavior. Minor density prevents a perfect score, but it remains efficient.

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

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

Given the tool has 6 parameters and an output schema exists, the description covers the core purpose, idempotency, and failure behavior. However, it lacks details on prerequisites (service must be registered) and error handling beyond failure receipts. The param gaps hurt completeness. It is adequate but not thorough.

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 by explaining parameters. It explains 'call_id' (used for idempotency) and implies 'service_id' (registered service) and 'tool' (which tool to call). However, it omits 'arguments', 'timeout_s', and 'payment_ref' with no details. The meaning of these parameters is left to the schema, which is insufficient for such low 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?

The description clearly states that the tool relays a tool call to a registered MCP service and notarizes the exchange. It uses specific verbs ('relay', 'notarize') and specifies the resource ('tools/call', 'receipt chain'). This distinguishes it from siblings like 'verify_receipts' which only verify, and 'get_receipt' which only retrieves receipts.

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 mentions idempotency on call_id, guiding the agent to use this tool for reliable, idempotent calls where replay should return cached results. It implies when not to use (e.g., if no receipt needed or non-idempotent behavior desired), but does not explicitly list alternatives or exclusions. This is clear but lacks full when-not guidance.

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

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

No annotations are provided, and the description does not disclose any behavioral traits such as idempotency, auth requirements, or side effects. The tool is implied to be read-only, but this is not explicit.

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 concise sentence with no wasted words. For a simple tool with no parameters, it is appropriately sized, though it could benefit from a bit more detail.

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 simplicity (no parameters, output schema exists), the description is minimal but lacks details about the output format or content. It is adequate but not fully informative for an agent invoking the 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?

There are no parameters, and the schema coverage is 100% (trivially). The description adds no meaning beyond the empty schema. Baseline score of 3 is appropriate as per guidelines.

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 'Fleet-standard self-description' clearly states the tool provides self-description of the agent. It distinguishes from sibling tools which cover specific functions like 'call_verified' or 'list_services'. However, it could be more specific about what aspects are described.

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 or why to use this tool. It does not mention alternatives or when it is appropriate to call (e.g., for introspection). Since there are no annotations, the description should fill this gap but does not.

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 convey behavioral traits. It only states 'Fetch a single delivery receipt by id'—no mention of side effects, permissions, or read-only nature, leaving significant gaps.

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

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

The description is a single, front-loaded sentence with no redundancy, achieving efficiency. However, it could be slightly expanded for clarity.

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

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

Despite having an output schema, the tool lacks behavioral context and parameter semantics. For a simple fetch, the description is minimally adequate but incomplete given zero schema coverage.

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%, yet the description adds no meaning beyond the schema for 'receipt_id' (e.g., format, example, or constraints). The parameter remains poorly explained.

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 'Fetch' and the resource 'delivery receipt', specifying retrieval by id. However, it does not differentiate from sibling tool 'verify_receipts'.

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 provided on when to use this tool versus alternatives like 'verify_receipts'. The description lacks context for appropriate usage.

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 bears full responsibility for behavioral traits. It only states the tool lists data but omits details like read-only nature, permissions, or pagination behavior. This is insufficient for full transparency.

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

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

The description is a single clear sentence with no extraneous words. It is front-loaded and 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?

For a simple list operation with no parameters and an output schema, the description is mostly complete. However, it could mention that the output schema defines the structure of services and counters.

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 no parameter explanation is needed. The description correctly adds no extra parameter info, meeting the baseline of 4.

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

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

The description clearly states the tool lists registered services with call/fee counters, providing a specific verb and resource. However, it does not differentiate from sibling tools like service_stats, which might also deal with service counters.

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 provided on when to use this tool versus alternatives such as service_stats or register_service. The description lacks context 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 are provided, so the description carries full behavioral disclosure. It transparently states idempotency on (url, provider) and the return of a content-addressed service_id. However, it omits details like side effects, authentication needs, or error handling, which are important for a mutation tool.

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 front-loads the core purpose, then adds key details (return value, idempotency, fee). Every word earns its place with no fluff or repetition.

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

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

Given 5 parameters, no annotations, and an output schema (not shown), the description covers the return type and idempotency but falls short on explaining all parameters, error conditions, or usage examples. It is adequate for basic understanding but not fully rich.

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 explains fee_minor as the per-verified-call fee in cents and implies url/provider parameters through the idempotency clause. However, it does not clarify description or payment_ref, leaving their meaning partially ambiguous.

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

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

The description clearly states the action 'Register a third-party MCP server' with specific constraints (https, public FQDN only) and a unique return value (content-addressed service_id). It also distinguishes from siblings like call_verified and list_services by focusing on registration.

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 prerequisites (https, public FQDN) but does not explicitly guide when to use this tool versus alternatives like list_services or call_verified. Idempotency is mentioned, which helps in understanding repeat calls, but lacks when-not-to-use 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?

No annotations are provided, and the description does not disclose any behavioral traits such as side effects, authentication requirements, or rate limits. The tool is described solely by its output.

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 very concise (one sentence) but lacks a subject-verb-object structure (e.g., 'Retrieves...'). It front-loads the outputs but omits important 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?

Despite having an output schema that could cover return values, the description does not provide parameter semantics or usage context, leaving the tool under-specified 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?

With 0% schema description coverage and no mention of the parameter 'service_id' in the description, the agent receives no meaning beyond the schema's type definition.

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 what data is returned (call counts, error counts, accrued fees) for a specific resource (one service). It distinguishes itself from sibling tools like list_services or call_verified.

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 tool versus alternatives. No exclusions or context clues provided.

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 exist, so description must convey behavioral traits. It fails to state whether operation is read-only or modifies state, required permissions, or potential side effects. The verb 'Recompute' could imply write, but 'audit' suggests read—inconsistent.

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, no filler. Front-loaded action verb followed by capability statement. 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?

Given simple schema (1 param) and presence of output schema, description covers core purpose. Missing usage and behavioral details prevent higher score, but for a straightforward verification tool, it is reasonably complete.

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

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

Schema has 0% description coverage, so description must add meaning. It ties service_id to the service whose receipts are recomputed, but provides no details on format, source, or validation. Baseline 3 achieved via minimal context, but more would improve clarity.

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 specific verb 'Recompute' and identifies resource as 'full receipt hash chain and fee ledger'. It distinguishes from siblings like get_receipt by emphasizing full chain recomputation and auditing. However, 'recompute' could be ambiguous about its operation type.

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 alternatives like get_receipt or call_verified. The phrase 'Any party can audit' implies general applicability but does not clarify exclusions or prerequisites.

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