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

Annotations already establish a safe, idempotent read, and the description goes well beyond them: it discloses the quota cost model ('one request of the user's quota per address'), the batching caps and their cause ('those layers are slow'), and the partial-result failure mode ('the rest is reported as skipped, not assessed'). The instruction not to present a truncated list as complete is exactly the kind of caveat annotations cannot carry.

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?

The description is front-loaded with purpose, then caps, then cost, then reporting guidance — a sensible order with no filler sentences. It is somewhat dense and run-on in the quota/partial-result sentence, which could be split for scanability.

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 available, the description still tells the agent what comes back ('returned as a split by recommended action') and how to report it ('Present the counts and name the addresses not to send to'). Combined with the cap, quota and skip semantics, it covers everything needed to invoke and interpret this 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 description coverage is 100%, so the meanings of emails, enrich and deliverability are already documented, including the cap of 10 when either flag is on. The description reinforces the cap rationale ('those layers are slow') but adds no new per-parameter semantics such as address format, deduplication, or whether invalid entries are reported. Baseline 3 is appropriate.

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 and resource ('Assess a whole list of addresses in one call') and immediately distinguishes itself from the sibling email_intel by scoping to bulk ('Same two questions as email_intel ... answered per address'). An agent can route between the single and bulk variants without opening either schema.

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 explicit when-to-use ('worth it on a cold list, not on a handful of contacts you already trust') and when-not, plus a hard operational boundary ('Up to 50 addresses per call, or 10 when deliverability or enrich is on ... split a longer list yourself'). It also names email_intel as the alternative for the single-address case.

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