Server Quality Checklist

Tool Scores

• get_day_statsB
  3.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must convey behavioral traits. It explains the timestamp semantics (24hr period starting at 00:00 UTC), return format, and sorting order. However, it does not disclose behavior for null bridge_id (whether it aggregates all bridges or errors), data availability, error handling, or rate limits.

  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 concise and front-loaded with the purpose, followed by parameter details and return format. It uses a structured list but could be more visually separated (e.g., bullet points). No unnecessary information is present.

  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?

  Given the presence of an output schema, the description explains the return format in detail (columns and sorting). It covers parameter semantics adequately. However, it lacks information on error conditions, pagination, or limits, which for a simple fetching tool is a minor gap.

  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?

  Schema coverage is 0%, so the description adds significant meaning beyond the schema. It explains timestamp as a Unix timestamp for the day, chain slug from list_chains, and bridge_id as optional from list_bridges. The timestamp semantics (24hr period starting 00:00 UTC) are explicitly defined, adding clarity beyond the schema's type-only definitions.

  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 clearly states the tool's purpose: fetching a 24hr token volume breakdown for a bridge on a specific day. It uses the specific verb 'Fetch and return' and identifies the resource (bridge). However, it does not explicitly differentiate from siblings like 'get_historical_volumes', though the day-specific nature and token breakdown provide implicit distinction.

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

  Usage Guidelines2/5

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

  No explicit guidance on when to use this tool versus alternatives. The description mentions parameters that reference 'list_chains' and 'list_bridges', suggesting prerequisites, but does not state usage context or exclusions. Sibling tools exist (e.g., get_historical_volumes) with no comparison provided.

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

• get_transactionsA
  3.8/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It mentions 'Fetch and return' assuming read-only, and specifies max limit of 6000. However, it does not disclose potential side effects, rate limits, authentication needs, or pagination behavior. Output description is vague ('key metrics').

  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?

  Description is well-structured with a clear purpose sentence followed by bullet points for parameters. Each sentence adds value and is not redundant. It is appropriately front-loaded but could be slightly more concise by removing the 'Returns a table' line as output schema exists.

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

  Completeness3/5

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

  For a tool with 6 parameters and no annotations, the description covers inputs adequately but leaves output vague ('key metrics'). Output schema exists, so return values are not required per rules, but operational details like pagination or error cases are missing. Completeness is average given context.

  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?

  Schema coverage is 0%, but the description provides detailed explanations for each parameter, including types, requirements, and formats (e.g., address format {chain}:{address}, limit max 6000). This adds significant value beyond the raw schema, though some clarity on default behavior for optional params could be improved.

  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?

  Description clearly states 'Fetch and return all transactions' with a specific resource (bridge) and scope (date range, table format). It explicitly distinguishes from siblings like get_day_stats and get_historical_volumes which are aggregated metrics, while this is raw transactions.

  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 does not explicitly state when to use this tool vs alternatives. It implies usage for fetching transaction data with filters, but lacks guidance on when not to use it (e.g., for summary statistics). The pointer to obtain bridge_id from list_bridges is helpful but not sufficient.

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

• get_historical_volumesA
  4.1/5.0
  Behavior3/5

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

  The description mentions the return format (table with columns), which adds basic behavioral context beyond the schema, but lacks details on data range, pagination, rate limits, or edge cases. Since no annotations exist, the description carries full burden but falls short of fully transparent disclosure.

  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 and well-structured: one main sentence stating purpose, followed by two bullet points detailing parameters. Every sentence provides necessary information without redundancy or fluff.

  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 parameter semantics and output columns adequately. However, it could be improved by mentioning data range availability (e.g., all-time or limited period) and ordering of results. The output schema helps, but missing this context slightly reduces completeness.

  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?

  With 0% schema description coverage, the description fully compensates by explaining each parameter: chain specifies the source via list_chains and includes the special value 'all', and bridge_id is sourced from list_bridges. This adds substantial meaning beyond the schema's empty descriptions.

  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 tool fetches historical volumes for a bridge, chain, or specific bridge on a chain, using specific verbs and resources. It distinguishes itself from sibling tools like get_day_stats (daily stats) and get_transactions (transaction details) by focusing on volume data and offering flexible filtering.

  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 when historical volume data is needed for a bridge or chain, but it does not explicitly state when to use this tool over siblings, nor does it provide exclusion criteria or alternatives. The context from sibling names is not leveraged in the description.

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

• list_bridgesA
  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 the full burden. It discloses sorting order ('last24hVolume descending'), return format (table with columns), and the effect of the optional parameter (include chain breakdowns). This provides sufficient behavioral insight for a read-only list tool, though it could mention data freshness or potential limitations like pagination.

  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 a concise two-sentence block with a bullet-style parameter explanation. It front-loads the main action and sorting, then clearly details the optional parameter. Every sentence adds value without redundancy or unnecessary detail.

  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?

  Given the tool's simplicity (1 optional parameter, output schema exists), the description covers the essential return columns and behavior. It adequately sets expectations for a list operation. However, it could mention whether data is real-time or includes a timestamp, and that it is a read-only operation (though implied). Overall, it is substantially complete.

  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 single parameter 'include_chains' is explained in detail: 'Whether to include current previous day volume breakdown by chain.' The input schema only provides type info (boolean/null, default false), so the description adds critical semantic meaning about the parameter's effect. This fully compensates for the 0% schema coverage.

  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 explicitly states 'Fetch and return a list of all bridges from DeFiLlama in a table format, sorted by last24hVolume in descending order.' It clearly identifies the action, resource, and key behavior. The sibling tools (get_day_stats, get_historical_volumes, get_transactions, list_chains) are distinct in function, so this tool's purpose is well-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 for obtaining a list of bridges, but does not provide explicit guidance on when to use this tool versus alternatives like list_chains or get_day_stats. No 'when-not-to-use' or alternative suggestions are given, leaving the agent to infer context from the tool's name and description.

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

• list_chainsA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description fully carries behavioral disclosure. It specifies the return format (table with columns) and ordering (TVL descending). It doesn't mention potential errors or latency, but for a read-only list, this 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?

  Three sentences, front-loaded with the main action, then parameter info, then output details. No wasted words, highly efficient.

  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 list tool with no parameters and an output schema, the description covers everything: what it returns, the format, and the sorting. No gaps.

  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?

  No parameters exist, so the schema coverage is 100%. Following the baseline rule (0 params = baseline 4), the description adds no extra parameter semantics but isn't needed.

  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 it fetches a list of all chain slugs from DeFiLlama in table format, sorted by TVL. This distinguishes it from sibling tools like get_transactions or list_bridges.

  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?

  It explicitly says 'No parameters required,' guiding the agent that no input is needed. It doesn't discuss when to use vs alternatives, but the simplicity makes this sufficient.

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