list_cached

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

The description adds value beyond annotations by detailing the behavior of each cache_mode: index only reads the manifest, refresh validates and prunes, and rescan rebuilds from sidecars. It confirms no network access, aligning with readOnlyHint. The mention of pruning/rebuilding implies local state changes, but annotations do not explicitly disallow this.

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 extremely concise, with two sentences that efficiently convey the primary purpose and explain the modes. There is no wasted text, and critical information is front-loaded.

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?

Despite having an output schema (not shown) and annotations, the description misses guidance on the 'download_dir' parameter. While the core purpose and mode behaviors are covered, the missing parameter info reduces completeness for a simple two-parameter tool.

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 0%, so the description must compensate. It explains the 'cache_mode' parameter with three values and their effects. However, it completely ignores the 'download_dir' parameter, leaving its semantics undocumented.

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 cached downloads offline, using 'list' as verb and 'cached downloads' as resource. It explains three cache modes, which adds specificity. However, it does not explicitly differentiate from siblings like 'get_cached' or 'fetch_paper', though the offline context helps.

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 explains when to use the tool (offline listing) and describes the three cache_mode options, guiding mode selection. However, it does not mention when not to use it or compare to alternatives such as 'get_cached' or 'fetch_paper', leaving usage context somewhat implicit.

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