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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), but the description adds real semantic context beyond them: both surfaces write to the same log, actor_kind 'agent' vs 'human' is decoded, and refusals are retained. It omits ordering/pagination behavior, so not a 5.

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?

Three short sentences, front-loaded with the core question the tool answers and followed by the actor_kind legend. The closing clause ('exactly what you want to be able to review') is editorializing that could be cut, which keeps it from a 5.

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 is a simple read with 100%-documented parameters and no output schema, so the description carries the burden of describing return shape — yet it never says what fields a row contains (timestamp, action, subject, outcome) or the default sort order. Given no output schema exists, this is a meaningful gap for an agent trying to interpret results.

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 100% for both parameters (limit with a stated default of 50, subject_id with an example 'SO-0003'), so the baseline is 3. The description adds nothing about how limit interacts with truncation or what subject_id filters on beyond the schema's example.

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 answers what the tool returns — 'What happened, who did it, and whether it was a person or an agent' — clearly identifying an audit-trail read. It distinguishes actor types but never differentiates itself from nearby log-style siblings such as gl_changes or crm_today, so an agent could confuse the audit trail with a change log.

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?

Usage is implied rather than stated: 'a blocked agent action is exactly what you want to be able to review' suggests the review/compliance use case. There is no explicit when-to-use, no when-not-to-use, and no named alternative (gl_changes, core_next_actions) that an agent should pick instead.

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