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

Annotations declare idempotentHint=true and readOnlyHint=false, but not WHY the tool isn't read-only. The description explains that: it queues a hosted job, which reconciles the non-read-only hint with the 'return events' phrasing. It also discloses append-only pagination semantics. It omits job lifetime/TTL and rate limits, 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?

Two sentences, zero filler, with the return shape front-loaded and the required follow-up call second. Every clause earns its place.

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?

With no output schema, the description correctly identifies the payload (audit events) and how to obtain it (get_job). It leaves pagination mechanics (how to page with afterSequence/limit) to the schema, which is reasonable, but the async return path could be slightly more explicit.

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 coverage is only 40%, so the description must carry more weight. It implies pagination (limit/afterSequence) and states append-only ordering, which helps orient the cursor parameter. But it says nothing about projectId, afterSequence semantics, or the requestId retry contract beyond what the schema already documents.

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 names a specific verb+resource: returning paginated, append-only project audit events. That is concrete and distinguishable from siblings like get_job or inspect_project. It stops short of explicitly contrasting itself with other read/inspection tools, so it lands at 4 rather than 5.

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 actionable routing guidance for the follow-up step ('use get_job to retrieve its result'), which is the critical usage detail for an async job tool. It does not state when to prefer this over other audit/project inspection siblings, but the workflow instruction is clear.

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