Server Quality Checklist

Tool Scores

• get_quotesA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full behavioral burden. It discloses important traits: internal decimal conversion for human-readable amounts, default addresses derived from PRIVATE_KEY, and Markdown return format including error cases. These go beyond schema basics, though it omits permission requirements or side-effect statements.

  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 detailed but efficiently structured: a one-line summary, then behavioral notes, then a parameter list, then a returns note. Every sentence adds value, and the parameter explanations are necessary given the tool's complexity. No wasted words.

  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?

  The description covers input semantics, defaults, output format, and error handling. It assumes valid chain keys and tokens come from sibling tools (list_chains/list_bridgeable_tokens), which is reasonable. The output schema (string) is addressed by noting Markdown formatting, so return value expectations are set without overspecifying.

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

  Parameters5/5

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

  Schema description coverage is 0%, and the description fully compensates. Each parameter is explained with format, examples, and defaults: src_chain_key shows 'ethereum', src_amount is described as human-readable with example, and optional addresses include fallback behavior. This provides far more semantic meaning than the bare schema.

  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 opening sentence clearly states 'Fetch quotes for a cross-chain token bridge transfer using the Stargate API,' providing a specific verb (fetch), resource (quotes), and context (bridge transfer). This distinguishes it from siblings like bridge_transfer (execution) and list_chains (chain info), so the purpose is unambiguous and differentiated.

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

  Usage Guidelines3/5

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

  The description implies usage as a pre-transfer step by describing retrieval of routes and quotes, but it never explicitly contrasts with bridge_transfer or states when not to use it. There is no guidance on alternatives, only implied context that this is the 'quote' stage before execution.

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

• list_chainsA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses that it fetches from the Stargate API and returns a formatted Markdown table, which is useful. However, it doesn't explicitly state that it's a read-only operation, mention potential network dependencies, or describe error behavior.

  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 concise, front-loaded with the main purpose, and includes only relevant details: the API source and return format. Every sentence earns its place.

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

  Completeness5/5

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

  For a simple zero-parameter tool, the description is complete: it states what it does, where the data comes from, and exactly what the return value looks like. No critical information is missing.

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

  Parameters4/5

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

  There are zero parameters, so the schema coverage is 100% and the baseline is 4. The description explicitly confirms 'Parameters: None' and adds a clear return format, adding value beyond the empty schema.

  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 states a specific verb ('Retrieve') and resource ('list of all blockchain networks supported by Stargate protocol'), clearly distinguishing it from siblings like list_bridgeable_tokens and bridge_transfer.

  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 clearly implies when to use the tool: whenever chain metadata is needed for cross-chain bridging. It doesn't explicitly mention exclusions, but the context is unambiguous and no alternatives are needed for this simple listing operation.

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

• list_bridgeable_tokensA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses that the tool directly queries the Stargate /tokens API, returns a Markdown table, and excludes the source chain from results—useful behavioral details. It does not mention potential rate limits or errors, but for a read-only listing tool, the transparency is adequate.

  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 well-structured with separate sections for parameters and return value. Every sentence adds value, and the examples and return format are presented without unnecessary verbosity.

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

  Completeness5/5

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

  Given the tool's low complexity (2 parameters, no enums, no nested objects), the description covers all essential aspects: what it does, how to use it, and what it returns. The output schema is not shown, but the description explicitly describes the return format as a Markdown table, so no critical information is missing.

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

  Parameters5/5

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

  The input schema only provides type 'string' for both parameters with no descriptions. The description compensates fully by naming each parameter and giving concrete examples ('ethereum' for chain, a USDC contract address for token), which is essential for correct invocation.

  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 clearly states the action: 'Retrieve a list of bridgeable destination chains and tokens for a given source chain and token.' It specifies both the resource (bridgeable tokens) and the scope (given source chain and token), and it is distinct from sibling tools like list_chains, get_quotes, and bridge_transfer.

  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 implies usage context: you would use this tool when you need to see available bridging destinations from a specific source chain and token. It does not explicitly name alternatives or exclusion criteria, but the purpose is clear enough to guide selection among siblings.

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

• bridge_transferA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and does so thoroughly. It discloses the internal flow: fetches a quote, signs transactions using the private key from .env, broadcasts sequentially, waits for confirmations, handles approvals, derives the source address from PRIVATE_KEY, and defaults destination address to source. It also lists error cases and return format.

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

  Conciseness4/5

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

  The description is well-structured: purpose sentence, process paragraph, parameter list, and return explanation. It is verbose but every sentence adds value. Some redundancy exists with the schema parameter list, but the extra semantics justify the length.

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

  Completeness5/5

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

  Given the tool's complexity (multi-step bridge transfer) and absence of annotations, the description is remarkably complete. It covers the execution flow, key derivation, approvals, sequential broadcasting, confirmation waits, return format, and potential error conditions, leaving few open questions for an agent.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description compensates by providing meaningful context for each parameter, including examples (e.g., 'ethereum', 'polygon'), clarifying that src_amount is human-readable, dst_amount_min is for slippage, and dst_address defaults to the source address if omitted.

  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 opens with a specific verb+resource: 'Execute a cross-chain token bridge transfer using the Stargate protocol.' This clearly distinguishes it from sibling tools (list_chains, list_bridgeable_tokens, get_quotes) which are informational and not execution-oriented.

  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 clearly implies when to use this tool (to actually execute a bridge transfer) and states that it fetches a quote internally, signaling that a separate get_quotes call may not be necessary. However, it does not explicitly say when NOT to use this tool or compare it to alternatives.

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