OpenChainBench

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

No annotations are provided, so the description carries full burden. It thoroughly discloses return payload structure, the 'unknown_slug' error for drafts, optional parameter scoping behavior, and citation instructions. This goes well beyond a simple 'get' and gives the agent realistic 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-organized with bullet points and a clear example section. It front-loads the core purpose and output details, keeping every sentence useful without unnecessary repetition.

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?

There is no output schema, but the description compensates by explicitly listing all return components, explaining error behavior, and providing citation instructions. With concrete usage examples and optional param semantics, the description is complete for reliable tool invocation.

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 parameters are already documented. The description adds meaningful context: examples for chain values, the fact that chain/region are optional and produce a global aggregate when omitted, and that they are only honored when the benchmark declares those dimensions.

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 opens with 'Returns full detail for one benchmark' and enumerates specific output components (rankings, sparkline, headline quote, methodology). This clearly identifies the tool's purpose and differentiates it from sibling tools like list_benchmarks and query_prom.

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?

Clear guidance is given for optional chain/region parameters, with concrete examples showing when to pass them and when to omit them for the global aggregate. However, it does not explicitly contrast with sibling tools or state when not to use this tool in favor of list_benchmarks or query_prom.

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 carries the full burden. It discloses that drafts are filtered out, describes the return format, and lists the fields returned. It could go further by noting ordering or potential absence of results, but it already provides meaningful behavioral context beyond a generic 'list' statement.

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 and well-organized. It leads with the core purpose, then usage guidance, then return shape, then a filter note. Every sentence contributes to understanding the tool with no 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?

For a simple, zero-parameter list tool, the description is complete. It covers purpose, usage, return format, and filtering. Since there is no output schema, the explicit field listing compensates adequately, making the tool self-explanatory.

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 tool has zero parameters, so the schema coverage is effectively 100%. The description adds value by explaining the meaning of the output fields and the filtering behavior, though it does not need to explain parameters that don't exist.

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 a specific verb ('Returns a flat index') and resource ('every published OpenChainBench benchmark') with a clear list of included fields. It also distinguishes itself from the sibling `get_benchmark` by explicitly saying to use that tool for specific slugs.

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?

Explicit usage guidance is provided: 'Call this first when the user asks a discovery question' and then use `get_benchmark` for details. This clearly states when to use this tool versus the alternative, along with example questions.

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 full responsibility for behavioral disclosure. It details allowed metric namespaces, refuses non-allowed metrics with a specific error shape (`{error, reason}`), and discloses return formats for both instant and range queries. This is comprehensive behavioral context.

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 long but every sentence contributes: scope, usage guidance, allowed namespaces, refusals, examples, and return types. It is well-structured with bullets and examples, making it scannable without 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?

For a raw query tool with no output schema and no annotations, the description provides all necessary context: what the tool does, when to use it, what metrics are allowed/refused, how parameters behave, and what to expect in the response. It is self-sufficient for the agent.

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 the baseline is 3. The description adds value with concrete examples showing how `query` is used, and clarifies `windowSec` + `steps` semantics (step duration = windowSec / steps). This goes beyond the schema's parameter descriptions.

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 states it is a 'Direct PromQL passthrough' for advanced questions that don't map cleanly to `list_benchmarks`/`get_benchmark`, and provides concrete example questions. This clearly identifies the tool's purpose and distinguishes it from its 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?

It explicitly says 'Prefer the higher-level tools first' and then lists specific use cases: custom time windows, derived metrics, histogram aggregations. It also explicitly mentions that queries referencing operational/internal metrics are refused, providing clear when-to-use and when-not-to-use guidance.

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