zkproofport-ai

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively communicates this is a read-only informational tool ('Get a comprehensive step-by-step guide') that doesn't perform mutations. However, it doesn't mention potential rate limits, authentication requirements, or response format details that would be helpful for a guide-fetching operation.

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 appropriately sized and front-loaded with the core purpose. The second sentence provides valuable context about the guide's contents, though it could be slightly more concise by grouping related concepts (e.g., 'how to compute signal_hash, nullifier, scope_bytes, merkle_root' could be 'how to compute required cryptographic inputs').

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 tool with no annotations and no output schema, the description provides good context about what the guide contains and when to use it. However, it doesn't describe the return format (e.g., whether it's markdown, JSON, or structured data), which would be important for a guide-fetching tool with no output schema defined.

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 100% description coverage, so the baseline is 3. The description doesn't add specific parameter semantics beyond what the schema provides (circuit enum values), though it does mention the guide covers specific technical topics like 'signal_hash' and 'merkle_root' that relate to the circuit parameter's purpose.

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's purpose with specific verbs ('Get a comprehensive step-by-step guide') and resources ('preparing all inputs required for a specific circuit'). It distinguishes from sibling tools by focusing on preparation guidance rather than listing circuits (get_supported_circuits) or executing proofs (prove).

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 explicit usage guidance with 'Read this BEFORE attempting proof generation,' creating a clear temporal dependency with the 'prove' sibling tool. It also implicitly suggests this tool should be used for preparation while 'prove' is for execution, establishing a workflow relationship.

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?

Despite no annotations, the description details the response structure, chains, addresses, and required inputs for circuits, disclosing all relevant behavior. It implicitly indicates read-only nature, though not explicitly stated.

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 verbose, including extraneous details like USDC addresses and authorized attestors that could be externalized. The first line is front-loaded, but overall efficiency is moderate.

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?

Covers all necessary aspects: flow, circuits, response fields, chain info, and payment addresses. Slightly over-inclusive but complete for a simple list tool without output schema.

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?

Input schema is empty, so description adds value by explaining the purpose and return fields beyond schema. Baseline 3 due to 100% coverage, but description's detailed context earns a 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 'List all ZK circuits supported by ZKProofport' and instructs to call it first for discovery, distinguishing it from the sibling tool 'prove'.

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?

Explicitly provides the correct flow (get_supported_circuits → prove), warns against using non-existent tool names, and sets context for when to use this tool (discovery) vs alternatives (proof generation).

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 fully bears the transparency burden. It discloses that the tool returns a redirect message (not the proof), explains timeout limitations, and details the multi-step x402 flow. It could have more explicitly described the exact redirect behavior, but overall it is highly transparent about what the tool does and its limitations.

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 long and includes a redundant repeat of the input schema (already provided in <input-schema>). The verifier addresses at the end may be unnecessary for tool invocation. However, it is front-loaded with the important warning and uses clear section headers. It could be more concise without losing needed information.

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 complexity (nested inputs, no output schema) and its role as a redirect initiator, the description provides extensive context: the x402 flow, alternative REST endpoints, verifier addresses, and parameter details. It effectively equips the agent to understand the broader process and redirect to the correct endpoint if needed.

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 100%, so baseline is 3. The description adds significant value beyond the schema by providing detailed hex length hints, optional field explanations (country_list, is_included), and a complete request body example in the description. This helps the agent understand format and context well.

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 'Submit proof inputs to generate a ZK proof' but immediately contradicts this by warning the tool is UNSUITABLE for proof generation and only returns a redirect message. The actual purpose is unclear—it might be to initiate the x402 flow rather than generate the proof, but this is not explicitly stated. The tool's function differs from its stated purpose, causing confusion.

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 tells agents when NOT to use the tool ('MCP tool calls have timeout limitations... UNSUITABLE') and provides the exact REST endpoint alternatives (staging and production). It also explains the full x402 flow, giving clear context for when the REST API should be used instead. This is exemplary guidance.

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