Autonomy — canonical service discovery

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

Beyond the readOnly/idempotent/destructive annotations, the description discloses meaningful behavior: payment and execution are safety-paused, entries can be LEGACY or BLOCKED and not sellable, and unknown capabilities/networks or unverified budget requests return no eligible matches. This materially changes how an agent should interpret results.

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 short sentences, front-loaded with the main purpose and followed by eligibility and safety caveats. It is efficient, though 'Read-only canonical Autonomy discovery' partly restates the readOnly annotation.

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 read-only discovery tool with no required parameters, the description covers invocation trigger, eligibility behavior, and safety state. It omits output format and per-parameter details, but the absence of an output schema and the availability of annotations keep this acceptable.

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 only 29%, so the description must compensate. It clarifies capability/network behavior, budget eligibility, and sellability/status, but it leaves asset and status semantics under-specified and does not explain the relationship between capability and asset. It adds some parameter-level meaning, but not enough to fully offset the sparse schema.

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

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

The description opens with 'Find capabilities' plus a concrete domain list (blockchain state, balances, token data) and labels itself 'Read-only canonical Autonomy discovery,' which separates it from the service/status sibling tools. The verb-resource pairing is specific and not a tautology.

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

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

It gives an explicit trigger condition ('when an agent needs blockchain state, balances, token data or other cataloged infrastructure') and signals what will happen for invalid/unverified inputs. It does not name alternative sibling tools, but the context is clear enough for initial 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 carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds genuine value with the upstream-provider-health disclaimer, clarifying that the tool reports the registry's local view rather than asserting external system status — behavioral nuance the annotations do not express. No contradiction with 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?

Two tight sentences with no filler. The primary purpose is front-loaded, and the clarifying scope disclaimer is appended without redundancy. 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 no parameters and no output schema, the description carries the burden of explaining what is returned; it names the three inspected aspects clearly. The absence of return-format details is acceptable for a simple, no-arg status tool, and the annotations already cover the operational 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?

The tool has zero parameters and the schema is trivially 100% covered (empty object), so per the rubric the baseline is 4. The description lists the inspection dimensions (version, commercial status, transport capabilities), which maps well to the intended return content even though no input parameters need elaboration.

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

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

The description uses a specific verb ('Inspect') with a defined resource (registry) and enumerates the concrete outputs: version, honest commercial status, and transport capabilities. It is clearly distinct in intent from siblings like discover/services, though it does not explicitly name them. The phrasing 'honest commercial status' is slightly idiosyncratic but conveys the report's content.

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 final sentence, 'This does not claim upstream provider health,' provides a negative scope exclusion — telling the agent what this tool is NOT for. However, it never names sibling alternatives (autonomy_discover, autonomy_service, autonomy_services) or states when to prefer them, leaving routing largely to inference.

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, idempotentHint, and destructiveHint=false. The description adds valuable context: payment/execution are safety-paused and catalog entries can be LEGACY or BLOCKED, not sellable. This goes beyond the annotations and gives the agent insight into possible service states 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?

Two sentences with no filler. The primary purpose is front-loaded, and each sentence adds distinct information (what is inspected and the current safety state). Efficient and well-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 simplicity (one parameter), annotations covering safety, and no output schema, the description is mostly complete. It indicates what information is returned (status, schema, payment readiness) and notes the paused state. Minor gaps include not specifying the response format or error behavior, but these are acceptable for a read-only inspection 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?

The schema has 0% description coverage, so the description carries the full burden. It only says 'by ID', which is redundant with the parameter name 'service_id'. It does not explain the format, constraints (beyond maxLength), or any expected value semantics. The description adds minimal meaning beyond the schema's type and name.

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 ('Inspect'), resource ('canonical service by ID'), and scope ('status, input/output schema and payment readiness'). It clearly differentiates from sibling tools by focusing on a single service via ID, unlike presumably broader discovery tools. The read-only nature is also highlighted.

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 when to use this tool (when you need details on a specific service by ID) but does not explicitly name alternatives or state when not to use it. There is no explicit routing to siblings like autonomy_discover or autonomy_services. The guidance is 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 declare readOnlyHint, idempotentHint, and openWorldHint, so the bar is lower. The description adds meaningful behavioral context beyond the annotations: catalog entries can be LEGACY or BLOCKED, are not sellable, and execution is safety-paused. This clarifies real-world limitations not visible in the structured metadata.

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, front-loads the core purpose, and every clause adds useful information: canonical discovery, read-only nature, safety-paused execution, and catalog status values. There is 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?

For a zero-parameter read-only discovery tool, the description covers purpose, availability scope, status constraints, and execution blocking. It does not describe the exact output shape, but with no output schema and no parameters, the provided context is sufficient for an agent to invoke it 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?

The tool takes zero parameters and schema coverage is 100%, so there are no parameter semantics to document. The description appropriately focuses on what the list contains rather than inputs.

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 a specific verb ('List') and resource ('canonical Autonomy service capabilities, actual availability, schemas and price readiness'), and identifies itself as read-only canonical discovery. It does not explicitly differentiate from similarly named siblings like autonomy_discover, but the scope is concrete enough to orient an 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 implies this is for read-only catalog/discovery use and explicitly notes that payment and execution remain safety-paused. However, it does not name sibling alternatives or state when to choose this tool over autonomy_discover, autonomy_registry_status, or autonomy_service.

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