benchmark_index_candidate

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds that cleanup is automatic and cleanup failures are durable, which is valuable behavioral context. It doesn't contradict the annotations.

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?

Two sentences, each providing distinct value: purpose and cleanup behavior. No redundancy or 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?

With 17 parameters, an output schema, and multiple phases, the description is high-level but leaves out significant invocation details such as the phase parameter, idempotency key usage, and filter definition. However, the schema and output schema compensate somewhat.

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?

Description provides no parameter-level detail; schema covers about 65% of parameters with descriptions, leaving several (online, is_unique, decision_id, database_name, lease_minutes, include_columns) unexplained. The description does not compensate for this gap.

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 specifies 'Benchmark a leased disposable index in a policy-allowlisted sandbox,' clearly identifying the verb (benchmark), resource (index candidate), and sandbox context. This distinguishes it from sibling tools like benchmark_tuning_candidate or benchmark_query_rewrite by focusing on a leased disposable index.

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 conveys that this is for benchmarking a temporary index in a safe sandbox, implying a testing use case, but it lacks explicit guidance on when to use versus alternatives like benchmark_tuning_candidate or what prerequisites exist. It also doesn't mention the screening/finalist phases from the schema.

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