Autonoma Agent Services

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

No annotations are provided, so the description must carry the full behavioral burden. 'Deterministic static' usefully signals no side effects and repeatable output, and 'public URL' plus 'non-sensitive' implies safety constraints. However, it does not state that this is a read-only operation, doesn't describe what a result looks like (no output schema exists), and doesn't say whether checks can fail-partial or time out.

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?

A single well-formed sentence with no filler. However, it is so terse that it omits essential information; brevity is achieved partly through under-specification rather than economy.

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 annotations, no output schema, three undocumented parameters (0% coverage), and a nested 'document' object, the description is too thin for the task. It omits what protocols are checked, what the result contains, and what constraints apply to the document input. The title carries information the description should contain.

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 but does not. It references 'URL' and 'JSON document' generically, but says nothing about the 'kind' parameter or its auto/a2a/mcp/openapi enum, which is the single most important invocation hint here. All three parameters are effectively undocumented beyond their type.

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 names an action ('Run deterministic static checks') and a target ('one public URL or supplied non-sensitive JSON document'), but it obscures the actual purpose. The title is far more informative, identifying it as an MCP/A2A/OpenAPI compatibility check. The description never states what is being checked for or that this evaluates protocol compatibility, which is the core resource. It separates itself from siblings only by implication (they are task/offer tools), not by explicit differentiation.

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 the sibling tools, nor when one should prefer URL input over document input. The 'non-sensitive' qualifier hints at a constraint but is not framed as usage guidance. An agent has to infer the entire use case from the title.

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 carries the full burden. It discloses that the operation returns current data and verified performance totals, implying a read-only lookup, but it does not mention permissions, rate limits, pagination, or explicitly confirm no 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?

A single front-loaded sentence with no wasted words. It states the core action and return scope immediately.

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 no-parameter list tool with no output schema, the description provides a minimal summary of returned content. It is adequate but leaves gaps around output shape, freshness, and usage context.

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, so the baseline is 4. The description appropriately does not invent parameter details, and the empty schema is self-evident.

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 clear verb ('Return') and specifies the resource ('current fixed-price services and verified performance totals'), so the agent knows it lists paid offers. However, it does not differentiate from siblings like task_capabilities or request_service, so it stops short of a 5.

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

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

No when-to-use guidance, prerequisites, or alternatives are provided. The description only states what is returned, leaving the agent to infer usage from the name.

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 behavioral burden; it does disclose an authority prerequisite, which maps to the authorization_attestation requirement and is genuinely behavioral. It does not disclose side effects, reversibility, rate limits, or the nature of the returned quote.

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 action and followed by the gating conditions; no filler. Slightly terse for the amount of undocumented parameter surface, but nothing is wasted.

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 4-parameter tool with no annotations and no output schema, the description is thin: it omits return/quote semantics, the meaning of request and deliverables, and how it relates to sibling tools such as request_service or task_capabilities.

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% across 4 parameters, so the description must compensate. It loosely hints at target_scope and authorization_attestation, but the required `request` parameter and the `deliverables` array are entirely unexplained in both schema and 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?

States a concrete verb pair ("Classify and price") and resource ("a bounded task"), so the agent knows the operation. However, it does no work to distinguish itself from siblings such as request_service or list_offers.

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?

"Requires authority to commission the work and a target scope" implies prerequisites and therefore the context in which the tool is valid. But there is no explicit when-to-use/when-not-to-use and no mention of alternative tools like request_service for non-quoting paths.

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 carries the full burden, and it does disclose one important trait: without payment_reference the tool returns payment requirements rather than executing work, and payment is in Base USDC. It does not cover authorization requirements, idempotency, what happens on an invalid payment reference, or whether target_scope/payer_address change behavior. Useful but incomplete for a no-annotation 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?

Two tightly packed sentences with the payment flow front-loaded immediately after the opening. The only waste is the near-tautological first clause, 'Request a service.'

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 five-parameter tool with no annotations and no output schema, the description leaves major gaps: four undocumented parameters, unstated auth/payment failure behavior, and no sense of what a successful non-payment call versus a paid call returns beyond the payment-requirements case.

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% across five parameters, so the description must compensate. It explains only payment_reference (a confirmed transaction hash); offer_slug, target_scope, payer_address, and authorization_attestation are left entirely unexplained in both schema and 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?

The opening sentence, 'Request a service,' largely restates the tool name (request_service) and title, adding little on its own. The second sentence does reveal the real behavior, a two-step USDC payment handshake, which clarifies the actual purpose. However, it never differentiates from siblings like quote_task or list_offers, so an agent must infer where this fits.

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 two-sentence flow effectively states the invocation pattern: call without payment_reference to receive payment requirements, then retry with the confirmed transaction hash. That is clear, actionable guidance on the first vs. second call. It lacks any explicit when-not or alternative routing (e.g. when to use quote_task first), which keeps it short of a 5.

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 doesn't disclose return shape, pagination, caching, or side effects – only a vague scope statement. For a discovery tool with zero annotation coverage this is thin.

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?

A single short sentence with no wasted words. It is appropriately sized for a no-arg discovery tool, though the phrasing is slightly abstract.

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 annotations and no output schema, the description is the only source of behavioral information, and it omits return format and inter-tool relationships. An agent knows roughly what topic the tool covers but not what it gets back or when to prefer it over list_offers.

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, so there is nothing to document; baseline 4 applies. The description introduces no parameters to confuse the agent.

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 what the tool surfaces ('bounded digital work this agent can quote and deliver'), which is more than a tautology but relies on abstract jargon. It doesn't clearly distinguish from sibling tools like list_offers, which also appear to enumerate deliverable work, so an agent must infer the difference.

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 indication of when to call this versus list_offers, compatibility_check, or quote_task. The description implies discovery but gives no context, prerequisites, or 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?

With no annotations, the description carries the full behavioral burden, and it only supplies two traits: cost ('free') and determinism. It says nothing about whether the call has side effects, whether it writes state, what evidence format is accepted, rate limits, or what the result contains.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though the brevity here reflects under-specification rather than disciplined editing.

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 tool with no annotations, no output schema, and an unconstrained input object, the definition supplies almost nothing an agent needs: not the evidence payload shape, not what the preview returns, not how it relates to the other trust/compatibility tools.

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?

Parameter count is 0, which sets a baseline of 4, but the schema is an open object (additionalProperties: true), so the agent genuinely needs to know what keys to supply. 'Supplied agent evidence' is the only hint and gives no shape, names, or types, so the description does not compensate for an effectively undocumented input contract.

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 names a verb ('Run') and a resource ('preview of supplied agent evidence') and adds distinguishing qualifiers ('free', 'deterministic'). However, 'agent evidence' is never defined, and nothing distinguishes this from siblings like compatibility_check or task_capabilities, which plausibly operate on the same domain objects.

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 when-to-use, when-not-to-use, or alternative-tool guidance is given. An agent cannot tell from this text whether the preview is a prerequisite for request_service or an alternative to compatibility_check. 'Free' hints at a cost-based selection motive but stops short of stating it.

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