v2_log_diagnose

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds behavioral value by disclosing that it fans out across every log surface in a single call and includes non-obvious checks (counter-vs-cap, retention, notification catalogues, syslog state), which sets expectations about scope and cost. It stops short of describing return shape or any auth/rate considerations.

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?

It front-loads the triggering question ('Why is the log empty?'), then answers it in two dense, waste-free sentences. The enumerated surfaces are long but each adds distinct information, and the closing caveat is well-placed.

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 complex multi-surface diagnostic with no output schema, the description conveys what evidence is gathered and when to invoke it, which is close to sufficient. It does not describe the shape of the response (e.g., per-surface verdicts), so an agent cannot predict the return structure before calling.

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% and the description never mentions siteId. With 0 required parameters, it is unclear whether omitting siteId yields an all-sites diagnostic or an error. The parameter name is a conventional identifier, so the gap is moderate rather than severe, but the description does not compensate for the absent schema documentation.

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 states a specific purpose (diagnose why logs are empty) and enumerates the exact evidence surfaces it aggregates: events, alerts, audit, stored-log counter vs. cap, retention policy, notification catalogues, and remote syslog state. The 'in one call' framing implicitly distinguishes it from the individual sibling tools (v2_events, v2_alerts, v2_audit_logs, v2_log_settings, v2_notifications) that cover the same surfaces one at a time.

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?

It gives clear situational context: 'Use this before concluding a quiet network — an empty log and a healthy network look identical.' This tells the agent exactly when the tool is warranted. It does not, however, explicitly name alternatives or when-not-to-use conditions (e.g., prefer the narrower log tools when you already know which surface to inspect).

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