Plan the minimum proof

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description still adds value by stating the output is deliberately minimal ('smallest...direct') and excludes speculation, which clarifies that the tool will not invent evidence or padded plans. No contradiction.

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, grammatically tight, with the key constraints front-loaded and no filler. Every word earns its place.

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 tool with seven parameters and no output schema, the description captures the high-level purpose but leaves out what the returned proof plan actually contains and how optional evidence/context influence the output. The title and schema help, but the description alone is not fully sufficient.

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?

All parameters have schema descriptions (100% coverage), so the baseline applies. The description itself adds no parameter-level details; it only states the overall goal, which the schema already encodes.

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 uses a specific verb ('Define') and a concrete object ('smallest direct evidence set and experiment') tied to 'technical claim,' so an agent can identify the core action. It does not explicitly distinguish prove_it from the sibling tools, so it stops short of 5.

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 'required to establish a technical claim' implies the tool is for planning proof rather than executing verification, but it gives no explicit when-to-use/when-not-to-use guidance and names no alternative sibling such as verify, audit, or reality_check. This is implied usage at best.

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