propose_edits

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

No annotations are provided, so the description carries the full burden, and it does so thoroughly. It discloses non-application of edits, exact return shape including the bare-array breaking change, skip_counts semantics, edit_mode behavior, mute no-op behavior for pauses, and that pipeline auto-tighten stays off.

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 dense but every sentence earns its place, covering purpose, return contract, mode semantics, and workflow in a compact block. It is front-loaded with the core purpose before diving into technical details.

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 description covers the return format, mode options, non-application, workflow position, and exclusions, which is strong given no annotations. It is slightly incomplete because project_path semantics and prerequisites are not stated, but the output schema existence and overall detail make it nearly sufficient.

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 description coverage is 0%, so the description must compensate. It richly explains edit_mode (ripple/mute, default source, mute behavior), but says nothing about project_path beyond its name. Since one of the two parameters is undocumented in both schema and description, the compensation is incomplete.

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: 'Propose filler/pause tighten edits for review' with the explicit caveat 'does not apply them.' Clearly names the operation and return object, and differentiates from siblings by explicitly stating 'Not NL cut-by-text (cut_* tools) or narrative focus (focus tools).'

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?

Gives explicit workflow guidance: 'listen-first review before apply_edits / approve_edits' and states the tool is not for cut-by-text or narrative focus operations. It also disambiguates edit_mode behavior for ripple vs mute, making it clear when each is appropriate.

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