list_cache_files

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

Beyond readOnlyHint=true, it discloses that with_data only inlines text and that binary files yield a placeholder rather than usable content. The metadata-field list further clarifies normal listing behavior, although the overall result structure is not specified comprehensively.

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?

Three short sentences front-load the purpose and then cover content behavior and sibling routing. There is virtually no filler, and the two get_cache_file mentions serve distinct cases: binary downloads and single-file reads.

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 read-only listing tool with four optional, fully documented parameters, this provides enough information to select and invoke it correctly. The explicit metadata list and placeholder behavior substantially offset the absence of an output schema.

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?

The schema already documents all four parameters, so the description need not re-explain every filter. It adds meaningful detail for with_data by clarifying the text-only limitation, binary placeholder behavior, and exact fallback for downloading binary content.

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 opening verb and scope identify exactly what is listed: files cached by scheduler jobs, with a parenthetical list of per-file metadata. The closing direction to get_cache_file also distinguishes bulk listing and metadata inspection from reading a single file.

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?

It gives explicit routing: use get_cache_file to read one file, and use get_cache_file with download=true for binary content. It also clarifies that with_data is suitable for inline text but leaves binary entries as placeholders.

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