write_prompt_file

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

With no annotations provided, the description carries the full burden of disclosure. It reveals that the operation is destructive in nature but backs up the previous version, affects all chats, and takes effect only on restart. It also mandates user confirmation for a specific file. This goes beyond the schema and gives the agent a solid understanding of side effects and prerequisites, though it omits details like error conditions or backup restore process.

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 highly efficient: two sentences convey the core action, backup behavior, global side effects, restart timing, and a confirmation requirement. Every sentence earns its place, and the primary action is front-loaded. There is no redundant or superfluous text.

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 mutation tool with no annotations but an output schema, the description provides sufficient context: what it does, the backup, the global impact, timing, and a confirmation caution. Minor gaps exist, such as behavior if the file does not exist or if backup creation fails, but these are edge cases that the agent can infer. Overall, the description covers the essential information needed to invoke the tool correctly.

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 input schema already covers both parameters with descriptions (name: 'Filename ending in .md, inside the prompts directory'; content: 'Full replacement text'), achieving 100% schema description coverage. The tool-level description adds no parameter-specific guidance, so the baseline of 3 is appropriate; the schema adequately conveys semantics without needing further elaboration.

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 opens with a specific verb and resource: 'Overwrite an on-disk prompt file, backing up the previous version.' This clearly distinguishes it from read-only siblings like read_prompt_file and list_prompt_files by stating the mutating action and the backup behavior. It also notes the scope ('affects every chat') and timing ('next ATLAS restart'), making the tool's role 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?

The description provides concrete usage context: the global effect, the deferred application, and the explicit requirement to confirm before changing system_prompt.md. It implies this is for on-disk prompt files as opposed to custom prompts managed by siblings like create_custom_prompt/update_custom_prompt, though it does not explicitly name alternatives or state when not to use this tool.

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