reef_scout

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

Annotations already declare readOnlyHint: true and idempotentHint: true, indicating safe, read-only behavior. The description reinforces this by stating 'not an editing agent' and describes the output as 'intent-weighted, explainable candidates.' It adds context about the nature of the returned data (from durable Reef facts, etc.), which goes beyond the annotations.

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 extremely concise: three sentences that front-load the main purpose, provide usage guidance, and set expectations. Every sentence adds unique value without redundancy or unnecessary detail.

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?

While the description adequately covers purpose, usage, and behavioral context, it lacks parameter-level details for a tool with 6 parameters and 0% schema description coverage. The presence of an output schema partially compensates for return value explanation, but the missing parameter descriptions leave a notable gap. Considering the tool's complexity, the description is not fully 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 description coverage is 0%, meaning the schema provides no descriptions for any of the 6 parameters. The tool description does not compensate: it only generically mentions 'query' and types of queries, but does not explain projectId, projectRef, focusFiles, limit, or includeRawEvidence. Given this gap, the description fails to add sufficient meaning beyond the schema's structural definitions.

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 purpose: 'turn a messy request into intent-weighted, explainable candidates from durable Reef facts, findings, rules, and diagnostic runs.' It distinguishes from siblings by emphasizing it's a scout view, not an editing agent, and advises using other tools after obtaining the packet. The verb 'scout' and resource 'Reef model-facing scout view' are specific and unique among siblings.

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 provides context for when to use the tool: 'App-flow queries prefer files/routes/findings; RLS/schema queries prefer database evidence.' It also states what not to use it for: 'This is a context scout, not an editing agent; use normal harness read/search after the packet.' However, it does not explicitly name alternative sibling tools for specific scenarios.

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