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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds a genuinely useful behavioral caveat — 'best-effort' signals the data may be approximate or incomplete — plus the window scoping. It stops short of noting freshness, auth scope, or rate limits.

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?

A single sentence with the verb and resource front-loaded and the window constraint appended. No filler, no restating of the title 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?

With an output schema present, return values need no explanation, and one optional parameter keeps the surface small. The description covers purpose and scope adequately; only freshness/latency expectations or empty-data behavior are unaddressed, which is a minor gap for a tool this simple.

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% and the single enum parameter's default (30d) is already documented in the schema. The description restates the 7d/30d options without adding format or behavior detail beyond the schema, so the baseline 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?

States a specific verb (fetch) and resource (deliverability metrics) with the scope of recent sends. It distinguishes itself from siblings, none of which report metrics, though it never names an alternative. The 'best-effort' hedge is informative but slightly muddies the promise of what is returned.

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?

The description implies usage — pull deliverability for recent sends — but gives no when-to-use trigger, no when-not, and no prerequisite or alternative. Since no sibling covers metrics, the agent can infer this is the only option, which keeps it at minimum viable rather than absent.

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