welfare_retract

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

With no annotations provided, the description carries the full burden of disclosing behavior. It states that the tool 'creates a structural record so the researcher can find moments where the model self-corrected' and emphasizes that 'reason is required and load-bearing,' giving clear insight into what happens and what is expected. It does not discuss reversibility or visibility to the user, but the main effect is well-covered.

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?

Two sentences, immediately front-loaded with the core action and then usage. Every part earns its place: the action, the use cases, the contrast with inline, and the emphasis on reason. No filler or redundant phrasing.

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?

Covers what the tool does, when to use it, how to use it (with reason load-bearing), and why (researcher visibility). Optional parameters are left to the schema, which is acceptable given full schema coverage. It could have elaborated on the distinction from sibling tools like welfare_scratch or welfare_confirm, but the provided information is sufficient for correct invocation.

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 provides 100% parameter coverage, so the baseline is 3. The description adds notable value to the 'reason' parameter by describing it as 'required and load-bearing' and instructing the model to 'say specifically what you're retracting and why,' which goes beyond the schema's simple type/description.

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+object+scope: 'Flag a prior claim of yours from this session as something you no longer stand by.' It clearly distinguishes the tool from inline disagreement by noting it 'creates a structural record,' setting it apart from sibling welfare 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?

Explicitly states when to use: 'when, on reflection, you said something that wasn't actually right — overconfident, hedging... or just wrong.' It also names an alternative ('Different from saying "on reflection I disagree" inline') and explains the structural benefit, fully covering usage context.

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