Eval Engine API

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

No annotations are provided, so the description fully bears the burden. It discloses the return values, cost, and need for valid benchmark IDs. It does not detail error handling, rate limits, or auth requirements, but the main behavioral aspects are covered.

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 two sentences: the first defines purpose and output, the second gives cost and usage hint. It is front-loaded, efficient, and contains no extraneous words. Every sentence adds value.

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?

Given 3 parameters, no output schema, and no annotations, the description covers purpose, input, output, cost, and usage hint. However, it lacks details on error scenarios, valid agent_trajectory format (only 'JSON string'), and benchmark-specific expectations. It is adequate but not comprehensive.

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 schema already documents each parameter. The description adds examples for 'benchmark_id' (e.g., 'qa-accuracy') but doesn't enrich meaning beyond the schema. Baseline is 3, and no significant extra semantics are provided.

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 clearly states the verb 'score' and the resource 'LLM output or agent trajectory against a benchmark rubric'. It specifies the output (score, metric name, reasoning summary, signed receipt) and references sibling tool 'list_benchmarks' for benchmark IDs, distinguishing it from 'get_benchmark' and 'list_benchmarks'.

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 tells agents to use benchmark IDs from 'list_benchmarks', providing examples. It implies usage for evaluation tasks but does not explicitly exclude cases or mention when alternatives might be better. The cost mention adds context for invocation decisions.

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?

No annotations provided; description implies read-only operation but doesn't disclose side effects or authorization needs. Adequate for a simple lookup.

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?

Single sentence, immediately clear, no unnecessary words.

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?

Given no output schema, description hints at return shape (criteria and rubric). Adequate for a simple retrieval tool.

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 coverage is 100% for benchmark_id; description adds that results include criteria and rubric, adding value beyond schema.

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?

Clearly states 'get detailed information about a specific benchmark including criteria and rubric', distinguishing it from sibling tools like list_benchmarks and evaluate.

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?

Implied usage (when you need details of one benchmark) but lacks explicit when-not-to-use or 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?

No annotations provided. The description adds that it's free and lists return fields, which is helpful. However, it doesn't disclose potential rate limits, authentication requirements, or that it is a read-only operation, which a simple list tool likely is.

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 extremely concise with two sentences and a list, front-loading the purpose. Every word adds value; no fluff.

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?

Given no parameters and no output schema, the description provides sufficient detail about the tool's output and examples. It could mention that it is read-only, but overall it is complete for this simple tool.

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?

No parameters exist, and schema coverage is 100%. The description adds value by explaining what the tool returns (IDs, names, descriptions, pricing) and lists example benchmarks, enhancing understanding beyond the empty schema.

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 clearly states the tool lists all available evaluation benchmarks, specifies what it returns (IDs, names, descriptions, pricing), and gives concrete examples. It distinguishes from siblings evaluate and get_benchmark by implying this is for listing all benchmarks.

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 mentions 'Free, no payment required,' which guides usage context. While it doesn't explicitly say when to use vs alternatives, the purpose is clear and the sibling names suggest differentiation.

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