list_files

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral detail beyond that: sizes are reported in bytes and long runs of time directories are collapsed, which tells the agent what the listing will actually look like.

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?

A single sentence with the core action front-loaded and two useful output facts in a compact parenthetical. No wasted words.

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 no output schema, the description should carry more of the return-format burden; it covers units and directory collapsing but says nothing about ordering, recursion semantics via depth, or whether subdirs are included. Adequate but with clear 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 67%: 'case' and 'subdir' are documented in the schema, but 'depth' (default 2) has no description anywhere, and the description does not compensate. Since the schema carries most of the load, baseline 3 is appropriate.

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?

States a specific verb and resource ('List files in a case') with a scoping qualifier that separates it from file-content tools like read_file and from list_cases/list_tutorials. It does not explicitly name a sibling alternative, but the resource is unambiguous.

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?

There is no guidance on when to choose this over list_cases, read_file, or get_dict, and no mention of prerequisites such as the case needing to exist or be accessible. Usage is only implied by the tool name.

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