List cached Cascade asset references

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

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint, setting a safe baseline. The description adds important behavioral details: the tool never reads Cascade directly, responses are JSON text, structuredContent is authoritative within size limits, and oversized responses return bounded _cache metadata. These go beyond annotations to inform the agent about response handling.

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?

The description is compact, using four sentences to convey purpose, usage context, and key behavioral traits. It front-loads the critical instruction ('Use after cascade_read'). While efficient, it could be slightly improved by integrating parameter guidance without adding bloat.

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?

Given the tool's complexity (6 parameters, no output schema), the description covers high-level context (purpose, cache behavior, tie to cascade_read) but lacks parameter explanations and detailed output structure. It mentions response format (JSON, structuredContent, _cache) but does not describe fields or pagination, leaving gaps for an agent to use the tool effectively.

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 description coverage is only 17%, with only asset_handle documented. The main description does not explain any of the other five parameters (pointer_prefix, reference_kind, etc.), nor does it provide usage hints for filtering. The description fails to compensate for the low schema coverage, leaving agents without guidance on how to customize queries.

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 the tool lists Cascade-native references from a cache, with specific sources (id/path pairs, asset nodes, metadata, etc.). It explicitly positions the tool as a companion to cascade_read and distinguishes itself by noting it never reads Cascade directly, differentiating it from cascade_read and other tools.

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 explicitly says 'Use after cascade_read,' providing clear context for when to invoke this tool. It implies the tool is for accessing cached data without live reads, but does not explicitly list when not to use it or name alternative tools for other scenarios. The guidance is functional but not exhaustive.

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