Winnow lossless context compaction

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

With no annotations, the description carries the burden. It discloses that the operation is lossless, preserves specific elements, and costs nothing. However, it doesn't clarify whether the tool modifies files in place or returns new text, nor does it describe error handling or side effects. This is a partial disclosure.

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 with no filler, front-loading the core action. It's efficient but slightly dense; the list of preserved elements is detailed but necessary.

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?

Without an output schema or annotations, the description leaves ambiguity about return values and file mutation behavior. It doesn't explain the relationship between the `text` and `file` parameters, nor does it specify what the tool returns. This is a significant gap for a tool with 5 parameters.

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?

All parameters have descriptions in the schema (100% coverage), so the description adds minimal extra meaning. It reinforces the goal and losslessness but doesn't explain parameter interactions or defaults beyond what the schema already provides.

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 tool's function: deleting irrelevant lines while preserving specific elements like paths, commands, error codes. It distinguishes itself from summarizing by emphasizing losslessness, but it doesn't explicitly differentiate from sibling tools like jev_rerank or jev_privacy_sanitize, so it's clear but not sibling-specific.

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 when to use it—when you need to compact context losslessly without summarizing—but it doesn't provide explicit exclusions or alternative tool references. The mention of 'log/grep/diff lines' gives context but no guidance on when not to use it or which sibling to choose instead.

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