Run a bundled sample claim

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description's only added context is the outcome space (contradicted, not_established, supported), which is useful but largely duplicated by the output schema. It says nothing about whether state changes, what sample is used, or what the scenario selection affects.

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?

A single short, front-loaded sentence with no filler. It is efficient, though the compression is part of why the parameter meaning remains ambiguous.

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?

Output schema exists, so return values need not be explained, but the one required input is undocumented and there is no guidance on when this tool applies versus its many verification siblings. For a tool whose entire purpose is to be a canned demonstration, the description should say that plainly.

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 0% for the single required 'scenario' parameter, so the description must compensate. The three listed values ('contradicted', 'not_established', 'supported') plausibly are the legal scenario names, which adds real meaning, but the sentence never explicitly labels them as such — it reads equally as return values, so an agent cannot be confident what to pass.

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 verb+resource phrase 'Run a bundled sample claim' is specific enough to convey that this exercises a canned example rather than a user-supplied claim, but the description never states what 'run' means (verification? classification?) nor distinguishes it explicitly from the sibling verify_claim. The trailing list appears to be possible outcomes, which helps but is left unlabeled and ambiguous.

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?

There is no statement of when to use this tool, when not to, or why one would pick it over verify_claim, verify_dsse, or run_vectors. An agent must infer from the word 'bundled' that this is a demo/smoke-test path rather than real verification.

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