Propose new guidance

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

Annotations already declare this is a non-read-only, non-destructive write, but the description adds genuinely useful lifecycle context that annotations cannot convey: the lesson 'is never authoritative until confirmed', meaning the write is provisional. It stops short of explaining what confirmation involves or how the pending state is surfaced, but the core behavioral caveat is disclosed.

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 short sentences with zero padding; the provisional nature of the tool is front-loaded in the first clause. Nothing in the text is redundant.

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 nine-parameter write tool with low schema coverage and no output schema, the description is thin: it covers the tool's role and lifecycle state but says nothing about the workflow/kind taxonomy, how lessons are reviewed or confirmed, or how to check status (e.g., twin_approval_status). Adequate for orientation, incomplete 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?

Schema description coverage is only 33%, so several of the nine parameters (kind, workflow, conditions, confidence, episode_ids, review_by) are undocumented in both schema and description. The description adds no parameter meaning whatsoever, leaving the agent to guess at fields like kind, workflow format, and conditions.

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 a lesson') plus the recipient ('for the principal to confirm'), so the agent knows this creates a provisional lesson rather than a settled fact. It does not explicitly distinguish itself from siblings like twin_record_decision or twin_record_correction, so sibling differentiation is left to inference.

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?

Usage is only implied: the phrase 'for the principal to confirm' suggests this is the pre-confirmation path, but the description never says when to choose this over twin_record_decision, twin_record_correction, or twin_request_approval, and offers no prerequisites or exclusions.

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