verify_source_chain

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

The description explicitly marks the tool as read-only ([READ]) and mentions that row-id gaps may indicate deleted audit rows, providing behavioral insight. However, with no annotations, it does not disclose potential side effects, authorization requirements, or performance implications.

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 concise, with a clear summary line and an Args section. It front-loads the main purpose and provides essential usage guidance without 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?

Given the tool's simplicity (3 parameters, no output schema), the description explains the purpose, output (chainHead, gap detection), and usage pattern. It does not cover error conditions or permissions, but for an audit verification tool, the provided information is sufficient for basic use.

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 description adds context to the 'source' parameter by linking it to list_audit_sources, and explains 'since/until' as ISO timestamps bounding the range. This adds value beyond the schema (which only defines types), but lacks format examples or boundary details like inclusive/exclusive.

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 verifies the source chain by returning chain head and detecting row-id gaps. The [READ] prefix indicates it's a read operation. It distinguishes from siblings like verify_bundle by focusing on source chain rather than bundle, but does not explicitly differentiate from query_audit_events.

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 advises recording the chainHead and re-running later to detect changes, implying periodic use. However, it does not explicitly specify when to use this tool versus alternatives like query_audit_events or verify_bundle, nor does it mention prerequisites or restrictions.

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