zkproofport-ai

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

No annotations are present, so the description carries the burden. It communicates that the operation is a read ('Read the current... guide') and hints that results are dynamic via 'current' and 'live deployment payment configuration.' However, it does not describe the return format, possible failures, or any access/authentication expectations.

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 lead sentence is front-loaded and information-dense, and the bullet list is easy to scan. The URL list repeats enum values somewhat, but it remains compact and useful.

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 read tool, the description supplies purpose, timing, and content scope. It is slightly incomplete in distinguishing canonical circuit IDs from supported aliases agreement, but an agent can still select the correct parameter from the enum and invoke the tool confidently.

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% and the circuit parameter is already documented with an enum and a description. The bullet list adds concrete endpoint URLs for five circuits but does not clarify which enum values are canonical IDs versus aliases, leaving some semantic ambiguity that the schema does not resolve.

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 a specific verb and resource: 'Read the current circuit-specific guide before proof generation.' It names distinct content areas (witness preparation, signature modes, verification chain, payment configuration) and clearly separates this read-only guide tool from the sibling prove and get_supported_circuits tools.

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 phrase 'before proof generation' explicitly instructs when the tool should be invoked relative to prove. It does not mention when not to use it or explicitly name alternatives like get_supported_circuits, but the context makes the intended usage unambiguous.

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 behavioral disclosure. It does so by listing the exact circuits and URLs and adding the caveat that 'payment networks are independent of circuit verification.' It doesn't explicitly state read-only/no-auth behavior, but the verb 'List' and zero-parameter schema make the operation's nature clear enough.

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 lead sentence is front-loaded and the bullet list is a compact way to show expected resource names and URLs. The 'Hosted tools' line and payment-network note add context, though they could have been trimmed slightly without losing core value.

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-input, no-output-schema listing tool, the description is nearly complete: it names every supported circuit, gives the canonical guide URLs, and tells the agent how to proceed. It omits minor details like response format or stability of the list, but these are unlikely to block a correct call.

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 already communicates zero parameters, and the description isn't obligated to document any. It could have explicitly said 'takes no arguments,' but with 0 params and full schema coverage this is not a meaningful 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 opens with a crisp verb+resource pair: 'List every supported circuit and canonical guide URL.' It clearly distinguishes this discovery tool from its siblings (get_guide reads a guide, prove runs a proof) by enumerating what the list contains.

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 establishes a clear workflow: call this to obtain the supported circuits and guide URLs, then 'Read each guide' for attestation source/input schema/verification chain. However, it doesn't explicitly say when not to use it or name get_guide/prove as the alternatives in a direct comparison.

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 provided, the description carries the full transparency burden and does so thoroughly. It discloses no hardware TEE attestation, the fact that the prover receives inputs, conditional encryption via teePublicKey, the 402 challenge/payment flow, and legacy header requirements.

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 long but well-structured and front-loaded with the endpoint and purpose. The workflow, circuit-specific options, privacy caveat, and guide links are each relevant; the content is dense but not padded, though a bit more visual separation would improve scannability.

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 no output schema, the description covers the invocation workflow, payment headers, circuit-specific action rules, privacy caveats, and authoritative guide links. It is slightly vague about the exact shape of a successful final response or redirect payload, but the operational context is unusually well specified.

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%, so the baseline is 3, but the description adds real parameter-level meaning: it explains circuit-specific optional action fields (domain_separator and action_hash), identity-only proof behavior, and when to encrypt inputs. This goes beyond the schema's generic 'circuit-specific prepared witness' 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 description opens with a specific verb-resource pair: 'Get the REST endpoint for long-running Noir proof generation.' It immediately clarifies that the tool redirects and does not generate a proof inside the MCP call, distinguishing it from sibling metadata tools like get_guide and get_supported_circuits.

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 step-by-step invocation flow and instructs the agent to read the canonical guide before preparing inputs, effectively pointing to get_guide for circuit-specific preparation. It gives clear usage context, though it never explicitly says 'use get_guide instead of prove for input schemas' or names exclusion conditions.

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