benchmark_propose

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

No annotations exist, so the description must disclose behavior. It mentions rejection of invalid proposals but omits what happens on success, side effects, authorization needs, or output format. This leaves significant gaps about tool behavior.

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 a single, information-dense sentence that front-loads the main purpose. It avoids fluff but could be slightly more structured for readability. Still, it is appropriately sized for a simple tool.

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, no annotations, and a complex nested input schema, the description should provide more context about return values, state changes, and integration with sibling tools. It only covers input validation criteria, leaving the overall workflow unclear.

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 0%, so the description must explain parameters. It partially explains the 'benchmarks' parameter by listing required fields, but does not clarify the 'runId' parameter or the exact semantics of fields like 'oracle' or 'qualityScale'. Two parameters remain under-documented.

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's action: 'Propose one or more benchmark scorecards built from real prior uses/failures.' It specifies the resource (benchmark scorecards) and distinguishes from siblings like benchmark_run or benchmark_freeze_maker by focusing on the proposal phase.

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 provides explicit validation criteria: each benchmark must have ≥1 task-value dimension, ≥1 resource/cost dimension, and ≥1 concrete case, otherwise rejected. This guides proper usage but does not contrast with when to use alternatives like benchmark_select or benchmark_freeze_maker.

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