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

With no annotations present, the description carries the full transparency burden and does so well. It discloses that 'No code executes', that passing 'does not prove external truth or independent reproduction', and that responses use 'term-evidence-vocabulary-v1' with each label's witness and limitation. It also adds a security constraint, 'Never include secrets'.

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?

Three dense sentences, each earning its place: the first states purpose and side-effect boundary, the second manages expectations, and the third describes the response and security constraint. No fluff or repetition.

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 no output schema and no annotations, the description supplies essential behavioral and return-value context, including response vocabulary and non-guarantees. It is slightly incomplete on how to compose 'checker' or interpret pass/fail outcomes, but the schema and referenced docs partially fill that gap.

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 50%, with descriptions for 'result' and 'dataset' but not for 'statement' or 'checker'. The description adds context by referring to the 'deterministic DSL' and by warning against secrets, but it does not explain the role of each parameter or how 'checker' relates to the DSL, leaving some compensation gaps.

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 states a specific action, 'Check a supplied public dataset/result', with a clear resource and mechanism, 'existing deterministic DSL'. It also distinguishes the tool from a mutating/publishing action by explicitly saying 'without publishing or spending write budget', which sets it apart from write-oriented siblings.

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 makes the intended use clear: use this tool to check data without publishing or consuming write budget. It gives an implicit when-to-use context, but it does not explicitly name an alternative tool or provide a when-not-to-use exclusion.

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