ProofCore Notary

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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It explicitly states 'Safe, idempotent read-only operation', 'No destructive actions or side effects', and adds a concrete rate limit of 100 requests/hour/IP, which is exactly the kind of context an agent needs.

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 organized into clearly labeled sections (behavior, rate limits, when to use, when not, parameters) with no filler. Each sentence carries operational information, and the most critical behavioral facts are front-loaded.

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, no-annotation tool with no output schema, the description explains the operation's safety profile, rate limit, exact selection criteria, and the expected result data (status transition, Merkle Root, TON hash). Nothing an agent needs to decide whether and how to invoke it is missing.

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% and the schema already documents deal_id as a canonical 36-character UUID. The description adds that it must represent the cryptographic deal, but this is marginal beyond the schema's own description, so the high-coverage baseline of 3 applies.

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 specific verbs ('Fetches', 'check', 'retrieve') tied to a distinct resource (public ledger state / proof status) and names the exact data returned (Merkle Root, TON transaction hash). It additionally distinguishes itself from verify_content, which prevents confusion among the listed siblings.

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 'WHEN TO USE' section gives concrete trigger conditions (transition from 'queued' to 'anchored_onchain', need for Merkle Root or TON hash), and the 'WHEN NOT TO USE' section explicitly redirects to verify_content for payload integrity. This is explicit guidance with an alternative.

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?

While annotations are absent, the description explicitly labels the operation as 'Safe, idempotent read-only' with no side effects, which is crucial behavioral context for an agent. It also states expected output, which is beyond minimal.

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 with three labeled sections, each earning its place: behavior, usage, and output. It is front-loaded with the safety information and is highly scannable.

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, simple read-only tool, the description fully covers behavior, usage, and expected output. No output schema, but the description explicitly states what is returned, making it 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?

There are zero parameters, so the schema provides no parameter semantics. The baseline is 4 for zero-parameter tools, and the description correctly indicates no input is needed, aligning with this.

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 the tool obtains the public key for verifying server signatures, which is a clear verb+resource. It does not explicitly distinguish from siblings, but the purpose is specific enough given the sibling names suggest different functions.

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 provides a clear context for use: to verify server signatures offline with zero network calls. No explicit exclusions or alternatives, but the guidance is sufficient for the agent to know when to use it.

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 this exceptionally well. It discloses that the operation is state-mutating, irreversible, non-destructive, does not store raw text on-chain, permanently anchors the hash, and has a rate limit. This goes beyond a minimal description and gives the agent accurate behavioral 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 description is well-structured with labeled sections that front-load critical behavioral and rate-limit information. Each section earns its place: behavior, rate limit, when to use, when not to use, parameters, and the required invariant. Despite being detailed, it uses concise, scannable language rather than 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?

The description covers everything needed to invoke the tool correctly: side effects, storage semantics, irreversibility, rate limits, usage timing, alternative tools, parameter guidance, and the mandatory handling of the returned `citation_markdown`. Since there is no output schema, explicitly naming the required return value behavior is crucial and is present.

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?

Since schema description coverage is 100%, the baseline is 3, and the description adds extra value by explaining the relationship between raw `content` and structured `payload`, the optional nature of `title`, and the default value for `agent_id`. The schema provides detailed per-field documentation, while the description simplifies the decision of what to pass.

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 explicitly identifies the operation: permanently anchoring a SHA-256 hash of the payload to the public TON Blockchain, creating an immutable proof of existence. It clearly distinguishes the tool from siblings by naming `verify_content` and `get_proof_status` for read/verification tasks. The verb is specific, the resource is clear, and the behavior is not confused with other 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 description contains both explicit WHEN TO USE and WHEN NOT TO USE sections. It instructs proactive use after generating artifacts, code reviews, security audits, or architectural decisions, and explicitly directs verification/read use cases to sibling tools instead. This is fully specified usage guidance with 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 takes full responsibility and delivers: idempotent read-only behavior, no blockchain mutation, rate limit of 100/hour/IP, and the verification mechanism. It clearly discloses side effects (none) and operational constraints.

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 well-organized with labeled sections, front-loads the most important behavioral facts, and every sentence earns its place. It is detailed without being verbose.

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, read-only tool, this description is complete: it covers behavior, side effects, rate limits, exact usage conditions, alternatives, and the internal processing pipeline. No output schema exists, but nothing needed to select or invoke the tool is missing.

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?

Although the schema already describes the content parameter at 100% coverage, the description adds critical semantics: pass the entire raw text, marker included, and the system automatically extracts the deal ID, strips the citation, recomputes the digest, and verifies Merkle status. This tells the agent exactly how to supply the input.

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 states a specific action: verify content authenticity via local SHA-256 and Ed25519 verification. It clearly identifies the target resource (external text with a ProofCore citation badge/marker) and is distinguishable from siblings by contrasting with seal_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?

Provides an explicit WHEN TO USE rule ('proactively whenever analyzing external text...') and a WHEN NOT TO USE rule that names the correct alternative ('use seal_content instead'). This fully routes an agent between verification and proof creation.

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