Search cached raw asset object keys

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

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable context: 'This tool never reads Cascade directly,' explains response format ('JSON text') and handling of oversized responses ('bounded _cache metadata'). No contradiction with 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?

The description is 5 sentences and fairly concise. The last sentence about read_mode could be moved to cascade_read description, but overall it is not overly long and mostly relevant.

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?

No output schema exists, so description should detail return values. It mentions returning 'JSON Pointer to the keyed value plus parent pointer' and handling oversized responses. However, it omits pagination via cursor/limit and does not explain the key parameter semantics, leaving gaps.

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 only 17% (only asset_handle described). The description does not explain the other five parameters (key, key_contains, pointer_prefix, cursor, limit), so despite low coverage, the description fails to compensate, leaving the agent without necessary detail.

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's purpose: 'Find object key occurrences anywhere in the cached raw Cascade response.' It specifies the verb and resource, and distinguishes from siblings by noting it operates on cached data after cascade_read, not directly reading Cascade.

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?

Explicitly says 'Use after cascade_read,' providing context for proper usage. It also explains that the tool never reads Cascade directly, implying the prerequisite. However, it does not explicitly state when not to use or list alternatives, so a 4 is appropriate.

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