Server Quality Checklist

Tool Scores

• seal_contentA
  3.6/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the full behavioral burden. It does disclose that this is a cryptographic, blockchain-based write and that a citation is returned, which implies permanence. However, it does not explicitly mention side effects such as the on-chain record being public, irreversible, or potentially requiring network or fee considerations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is only two sentences and has no fluff. The first sentence establishes what the tool does; the second gives the trigger for using it and a mandatory operational rule. The information is front-loaded and easy to parse.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For the core required parameter, content, and for the expected follow-up action, the description is sufficient: provide content, get a citation, and add it to the answer. Since an output schema exists and the other parameters have defaults, the lack of detail on title and agent_id is a minor gap. The main omission is explaining the real-world implications of sealing something onto a blockchain.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description needs to compensate for the lack of parameter explanations. It only clarifies that content is 'text/code/audits'—title and agent_id are not described beyond their schema defaults and names, leaving their roles partly implicit.

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

  Purpose4/5

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

  The description names a specific action ('seals'), a resource ('text/code/audits'), and a concrete target (TON Blockchain), so an agent can tell what the tool does. It even reframes the purpose as notarizing findings. It does not explicitly contrast with the sibling get_proof_status, but the core purpose is clear.

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

  Usage Guidelines4/5

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

  The description explicitly says when to use it: 'Use this tool to notarize your findings.' It also provides a required follow-up behavior—append the returned citation to the final answer—which helps the agent use the result correctly. It does not give a when-not-to-use clause or call out the sibling alternative.

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

• get_proof_statusA
  4.2/5.0
  Behavior4/5

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

  The verb 'Retrieves' discloses a non-mutating action, and the description enumerates exactly what data will be obtained, giving an agent a clear behavioral model. Since there are no annotations, this description partially carries the transparency burden, but it does not mention auth requirements or possible errors.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One sentence with no tangential or redundant language. The primary verb and object precede the context, making the description easy to parse and efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a one-parameter read operation with an output schema available, the description outlines the required data categories and the prerequisite condition ('sealed deal'). It is slightly sparse on peripheral context such as sibling-tool routing, but adequate for correct invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema contains one required parameter, deal_id, with no description and 0% schema description coverage. The description's 'for a sealed deal' provides context that deal_id refers to an already-sealed deal, but it does not explain the format or provenance of deal_id, leaving some semantic burden on the parameter name.

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

  Purpose5/5

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

  The description uses a precise verb ('Retrieves') and names specific returned artifacts: cryptographic manifest, Merkle path, and TON transaction status. The qualifier 'for a sealed deal' differentiates it from the sibling seal_content, which corresponds to creating/sealing a deal.

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

  Usage Guidelines4/5

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

  The phrase 'for a sealed deal' clearly implies that this tool is for deals that have already been sealed, which provides usage context. It does not explicitly name seal_content as an alternative or state when not to use it, but the contextual guidance is clear enough.

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