predict_performance

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

Annotations already declare the tool read-only and idempotent. The description adds meaningful context beyond that by revealing the cost ($0.05 USDC), the bounded-evidence scope, and the output characteristics (confidence, missing metrics, caveats). No contradiction with the annotations exists.

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 sentence, front-loads the cost, and conveys the verb, scope, outputs, and caveats without redundancy. Every word 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?

With 15 parameters and zero schema descriptions, this one-sentence description is insufficient for correct invocation. An agent cannot determine the meaning of bounded evidence, the semantics of max_evidence, decode_context_depth, or the kv_cache fields, and the description does not clarify how this tool relates to siblings. The output schema reduces the need to explain return values, but parameter selection remains underspecified.

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%, and the description does not explain any of the 15 parameters. It only indirectly maps predicted outputs (throughput, memory, power) to the requested_metrics enum, but gives no guidance on model, hardware_system, prompt_tokens, or optional knobs like max_evidence, quantization, and kv_cache_type. The description fails to compensate for missing schema parameter documentation.

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 names a specific verb ('predict') and a clear resource ('configuration throughput, memory, and power'), and it signals the prediction is based on bounded StackBench evidence with confidence and caveats. This distinguishes it from siblings like search_evidence and recommend_deployment, so an agent understands which function is being offered.

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 phrase 'from bounded StackBench evidence' implies the tool is meant for prediction grounded in existing evidence, and the mention of 'confidence, missing metrics, and caveats' suggests when its output is appropriate. However, there is no explicit when-to-use guidance, no exclusions, and no reference to alternatives such as recommend_deployment or check_deployment_fit.

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