Search email delivery records

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds behavior not present in the structured data: results are ordered newest first, and the default result set is narrowed to failures and deferrals over a 24-hour window, which materially shapes how an agent interprets an empty response.

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 core action and the diagnostic intent front-loaded and the default scope trailing as supporting detail. Every sentence 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?

For a five-parameter, all-optional, read-only search with a fully documented schema and no output schema, the description covers purpose, ordering, and default filtering adequately. It could say slightly more about what a returned record contains or that results are capped by limit, but nothing needed to call the tool correctly is missing.

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%, with every parameter documented including defaults, ranges, and enum values for statuses. The description only restates the two defaults and adds no filtering syntax, matching rules, or guidance on combining sender/recipient/statuses beyond what the schema says, so the baseline of 3 applies.

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 gives a specific verb and resource ("Search the server's mail delivery records") plus the intent behind it ("work out why a message did not arrive"). No sibling in the list touches mail delivery logs, so the tool is unambiguously distinguishable from the account, DNS, disk, and error-log tools.

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 names a concrete use case — diagnosing non-delivery — which effectively tells the agent when to reach for this tool, and it explains the default scope (failed and deferred, last 24 hours) that applies when no parameters are supplied. It stops short of stating when not to use it or pointing at an alternative for successful-delivery auditing.

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