Get cached raw asset value

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

Beyond annotations (readOnly, idempotent), the description reveals that the tool never reads Cascade directly, supports slicing with offset/length, returns JSON text, and that structuredContent is authoritative for fitting responses. This adds valuable behavioral context.

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?

Four front-loaded sentences concisely convey purpose, usage, behavior, and edge cases. No redundant information; every sentence adds value.

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?

Without an output schema, the description explains response types (JSON text, structuredContent, oversized cache metadata) and links to cascade_read_response. It covers parameter behavior (slicing, pointer) and dependency on cascade_read, providing a complete picture.

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% (asset_handle and pointer have descriptions; offset and length lack descriptions). The description adds context for JSON Pointer and slicing, but does not fully define offset and length parameters. Baseline 3 due to partial coverage, with slight improvement from description.

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 uses specific verbs and resources: 'Retrieve the exact raw cached value at a JSON Pointer' and states it should be used after cascade_read, clearly distinguishing from sibling tools like cascade_read and cascade_read_response.

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' and explains when to use structuredContent vs _cache metadata. It also contrasts with cascade_read for oversized responses, but does not provide explicit when-not-to-use or alternative tool names.

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