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

Annotations already cover read-only/idempotent/non-destructive, yet the description still adds real value: newest-first ordering, the exact set of logged statuses, the fact that 'failed' means a network write was refused, and that rollback availability is a per-run field rather than an action. It does not describe pagination defaults, but the schema does.

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 compact sentences with the essential framing (log, ordering, inclusion rule) front-loaded, plus one exclusion clause. The em-dash aside about condition verdicts and touched entities is dense but every clause carries information.

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 six-parameter read tool with no output schema, the description supplies what the records contain (condition verdicts, touched placements/bids/status, rollback eligibility), which is exactly what is missing structurally. Filtering and paging semantics are left to the schema, which documents them adequately.

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?

With 83% schema coverage the baseline is 3, and the description earns above that by giving meaning to the status enum values (applied / rolled_back as state-changing outcomes, failed as a refused network write). rule_id and campaign_id get no narrative treatment, leaving a minor gap.

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 concrete resource and scope: an auto-rule firing log, newest first, covering runs that applied/rolled_back or failed on a refused network write. That is enough to distinguish it from list_auto_rules (the rule definitions) and get_auto_rule, though neither sibling is named explicitly.

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?

Clear guidance on what is and is not retrievable: 'Conditions not met' runs are absent and live in each campaign's last_result instead, and rollback is panel-only so the agent should not hunt for a rollback tool here. It stops short of naming an alternative tool for the last_result path.

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