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

Annotations already disclose read-only, idempotent, non-destructive behavior. The description adds the troubleshooting context (when delivery is suspected to have failed) but not additional behavioral details like response shape or field meanings. It does not contradict any annotation.

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 sentences, no fluff. The central action and resource are in the first sentence, and the 'when to use' is in the second and third. Perfectly front-loaded and efficient.

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?

Despite having no output schema, the tool is simple enough that the description plus schema cover what an agent needs: the resource, the trigger, and the safe read-only behavior. The only gap is that 'Realtime' from the title isn't echoed in the description, but 'recent' suffices for this low-complexity tool.

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 covers destination_id with a thorough explanation and a warning not to use the Unipile endpoint ID, while limit has type/default/bounds but no prose. The tool description doesn't elaborate on limit's meaning beyond what the schema gives, so it adds minimal value beyond the existing 50% schema coverage.

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 opens with a specific verb ('Inspect') and resource ('recent Unipile webhook delivery conversations for this destination'), which clearly differentiates it from sibling tools like webhook_test_destination or webhook_get_destination. It also frames the tool's role in troubleshooting delivery failures.

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 explicitly names two trigger conditions ('agent/n8n receiver did not wake' and 'test event was not observed') and contrasts with 'guessing whether delivery occurred.' However, it does not name any alternative tool or exclusion criteria, so it stops short of the 5-level.

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