List Files

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

Annotations already cover read-only, idempotent, non-destructive behavior, lowering the bar. The description adds useful context about return fields (name, type, size) and the optional search filter, which helps the agent understand what to expect from a call. No contradictions.

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 two sentences, front-loaded with the primary purpose, then the optional filter, then a clear pointer to read_file. Every sentence earns its place with zero redundancy.

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?

With strong annotations, a complete output schema, and a simple listing use case, the description covers purpose, filtering, and the natural follow-up action (reading a file). No significant gaps remain.

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 100% and the description adds only a small restatement of the search filter (already in schema). It doesn't provide additional detail like input formats or edge cases beyond what the schema offers, so the baseline 3 applies.

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 files in a course with specific metadata (name, type, size), and distinguishes itself from read_file by pointing to that tool for text content. This goes beyond a simple restatement and effectively differentiates within the sibling set.

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 provides clear context that this is for listing files and explains how to filter with 'search'. It also names read_file as an alternative for getting the text of a single file. However, it doesn't explicitly exclude sibling tools like course_content or get_page, so it's not a full when/when-not guide.

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