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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: it aggregates the inbox placement window together with the latest health check of every connected mailbox, and returns results ordered worst first with remediation actions attached.

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, front-loaded with the core question the tool answers, then the data it combines, then the usage trigger. No filler and nothing repeated from the schema or annotations.

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 read-only aggregate with one optional param and no output schema, the description covers the sources (placement window, auth records, blacklist listings, per-mailbox placement) and the output shape at a high level (ranked issues plus fixes). Precise return fields are not enumerated, but no critical calling information 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?

There is a single optional parameter with 100% schema description coverage, so the schema already explains 'days' and its default. The description refers only obliquely to 'the window' without adding format or semantics beyond what the schema provides, matching the baseline for fully documented params.

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?

States a specific diagnostic verb+resource: it surfaces what is wrong with deliverability across the workspace, ranked worst first, each item paired with a fixing action. It is clearly distinguishable from siblings like get_sender_reputation or get_inbox_placement_stats_by_date, which cover only one mailbox or one metric.

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?

Gives an explicit trigger: 'The best first call when asked why are we landing in spam,' which tells the agent to prefer this over narrower siblings. It stops short of naming those alternatives or stating when-not-to-use it, so it is strong context rather than full routing guidance.

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