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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond them: it discloses rate-limit sensitivity on polling and decodes status semantics ('importing/verifying' = still pending, 'finished' = task ended). It stops short of covering other terminal states (e.g., failed/cancelled) or what happens with an unknown id.

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?

Four short sentences, purpose first, then exclusion, then polling constraint, then status glossary — all front-loaded with no filler. The final sentence is dense and lower-case, and the glossary is partial, so it's tight but not maximally clean.

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 one-parameter read-only polling tool with full annotation coverage and no output schema, the description covers purpose, exclusion, rate limits and status interpretation. The remaining omissions — meaning of `id`, the full set of status values, and any sense of what 'aggregate results' contains — are modest but real for an agent that has no output schema to fall back on.

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 one required parameter with 0% schema description coverage, and the description never explains it — nothing says `id` is the bulk task identifier returned by bounceban_create_bulk_verification or what form it takes. With a single trivial parameter the gap is small, but the description adds no meaning beyond the schema's own constraints.

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 and resource: 'Read progress and aggregate results of an existing bulk task.' It partially differentiates from siblings by ruling out verification ('Does not start verification'), which separates it from bounceban_create_bulk_verification, but it never contrasts with bounceban_bulk_results, whose purpose ('aggregate results') it partly overlaps.

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 gives real operating context: an exclusion ('Does not start verification') and polling guidance ('Wait between polls and honor account rate limits'). What's missing is an explicit routing statement for the closest alternative, bounceban_bulk_results, so the agent must infer which to call for full per-email output.

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