download_files

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

The description discloses behavior the annotations cannot express: dest_dir is created if missing, nested folder-module structure is preserved by default, and the exact conflict policy (skip vs. rename to 'name (2).ext'). This usefully extends the annotations' idempotentHint/destructiveHint rather than repeating them.

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?

Front-loaded with purpose and the overwrite guarantee, then a tight bullet list where each entry maps to a parameter or decision. Slightly dense but no filler sentences.

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 write-to-disk tool with no output schema, the description covers naming, destination handling, and conflict resolution well. Missing only the meaning of the required 'course' argument and any mention of how download results/errors are reported.

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 carries the full burden, and it documents four of the five parameters (files, dest_dir, save_as, on_conflict) with formats, defaults, and examples. The required 'course' parameter is left completely unexplained, which is the one real gap.

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 first sentence gives a specific verb and resource ('Download course files into a local folder') plus an immediate behavioral fact ('existing files are never overwritten'). It does not, however, distinguish itself from siblings that also touch files, notably read_file and mirror_course, so an agent still has to infer the boundary.

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 'files' bullet tells the agent exactly where the input refs come from (get_course_outline / get_announcements / check_updates), which is real routing guidance. It stops short of when-not to use it or naming mirror_course as the whole-course alternative.

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