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

Annotations already cover readOnly, idempotent, and non-destructive hints. The description adds valuable context: it clarifies that the tool never pays or requests private bytes, explicitly states that no error cases exist beyond upstream_failure, and explains how inconsistencies are represented (data vs. error). This goes well beyond 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 packed with necessary information. The purpose is front-loaded, and the behavioral clarifications are concise. No filler or redundancy.

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 parameterless tool with strong annotations, the description fully covers what the tool does, its scope (107 levels), the meaning of valid results, and error handling. It even clarifies what the tool does NOT guarantee (image access, payment, feeling, adoption). Nothing critical is missing.

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?

The tool has zero parameters, and the schema coverage is trivially 100%. Per the baseline for 0 params, a 4 is appropriate. The description doesn't need to explain parameters, and it doesn't.

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 clearly states a specific verb (audit) and resource (all 107 textual levels vs. physical work ids and consultation endpoints), and it distinguishes this verification tool from the sibling tools by its read-only auditing nature. It's unambiguous about what it does.

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 gives clear context: it's a read-only audit that never pays or requests private bytes, and it clarifies that inconsistent mappings are returned as data rather than errors. However, it doesn't explicitly mention alternatives or when not to use it, though the siblings are clearly different actions. The safety guidance is strong.

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