reef_learning_review

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint. Description adds detail: 'Suggestion-only', 'Never writes durable knowledge', lists data sources (resolved findings, repeated rule history, etc.). No contradictions.

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, front-loaded with main action, no unnecessary words. Highly efficient.

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 has 9 parameters (no required), an output schema, and is suggestion-only. Description covers core behavior and safety but lacks details on output format, error handling, or edge cases like empty results. Adequate but not comprehensive.

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 coverage is 0%, so description must compensate. It hints at data sources (resolved findings, recent tool runs) but does not systematically explain each of the 9 parameters. Many params like mode, limit, since, projectId remain unexplained.

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 verb 'propose' and resources (rule-pack, sentinel, etc.) and highlights it's suggestion-only. It distinguishes from sibling tools like list_reef_rules or reef_instructions by emphasizing no writes.

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 (suggestion) and when not (if writing is needed). Provides an alternative path ('explicit separate write path') though does not name specific sibling tools.

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