list_prompt_files

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the files are system-level defaults, that editing them has global effect, and that changes take effect only after restart—important context for an agent deciding whether to modify them. Though it doesn't explicitly say the tool is read-only, 'List' implies that, and the caution about editing is a meaningful behavioral signal.

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 action. The second sentence provides necessary context about defaults and the impact of editing, which earns its place. It is slightly verbose for such a simple action but remains efficient and well-structured.

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?

Given zero parameters and an output schema (not shown but flagged as present), the description need not explain return values. It fully covers what the tool does, the distinction from the per-user library, and the operational consequence of editing—making it complete for an agent to decide when and whether to invoke it.

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 tool has zero parameters and the schema coverage is trivially 100% (empty properties object). The description correctly omits parameter details since none exist. Per the baseline for 0-parameter tools, a score of 4 is appropriate; the description adds nothing about parameters because there is nothing to add.

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 action (List), the resource (markdown prompt files), and the specific scope (defaults ATLAS loads from disk). It explicitly distinguishes from the per-user library, aligning with sibling list_custom_prompts, so an agent can immediately tell them apart without inspecting schemas.

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 says these are 'separate from the per-user library above', implying that list_custom_prompts is the alternative for user-specific prompts. It also warns that editing these files affects every chat and requires a restart, which informs usage context. However, it does not state explicit conditions like 'use this when you need system defaults' or 'do not use for user prompts', leaving some inference to the agent.

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