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

Annotations already cover the safety profile (readOnly, idempotent, not openWorld). The description adds real behavioral context beyond them: results are limited to 'public' capabilities, and frozen capabilities are flagged explicitly in the output. It stops short of describing pagination or result size, which matters for a list-everything tool.

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 tight sentences with no filler; the return contents are front-loaded and the frozen-marking caveat follows. Nothing redundant.

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 zero-parameter read tool with no output schema, the description adequately conveys what fields are returned and the frozen-state marker. Pagination/volume behavior is the only notable omission.

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?

Zero parameters, so the baseline of 4 applies. The description correctly indicates no filtering input exists, consistent with the empty schema.

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?

States a specific verb (List) and enumerates the resource contents (capability descriptions, schemas, prices, endpoints), so the agent knows exactly what comes back. It does not explicitly distinguish itself from the sibling find_capability, leaving the browse-vs-search distinction to inference.

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 word 'List' and the zero-argument schema imply a browse-all operation, but the description never states when to use this instead of find_capability or next_best_capability. Usage is only implied, with no exclusions or routing guidance.

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