save_cxt

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

The description explicitly mentions the refusal of source overwrite unless allowed, which adds behavioral detail beyond the annotations (readOnlyHint: false, destructiveHint: true). It doesn't contradict annotations, and it gives a key safety behavior. However, it lacks details on validation failure or side effects.

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 concise and to the point, but lacks structured guidance like parameter explanations or example usage. It is minimal but clear for the core action.

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?

The tool is a write operation with a safety flag, but it doesn't explain when to use it (e.g., after editing) or what happens to the existing file. It provides basic context but misses edge cases like validation failure or side effects.

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 schema lists five parameters (backup, project_id, output_path, expected_revision, allow_source_overwrite) with no descriptions. The description only hints at allow_source_overwrite. There's no explanation for expected_revision or backup, so the semantics are unclear for agents.

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 ('Validate and save edited source') and the target format ('as CXT'), making it distinct from siblings like apply_program_patch or replace_rung. It's a specific verb+resource statement.

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 implies usage after editing source and mentions validation, but it does not explicitly contrast with alternatives like 'apply_program_patch' or state when not to use this tool. Some context is given, but no exclusions or comparisons.

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