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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real behavioral context on top: results are capped at 50 rows, invalid and risky addresses are ordered first, the full list is never returned, and the call is 'Free' (no credit cost, meaningful given the get_credits sibling). This is exactly the kind of truncation and cost disclosure annotations cannot convey.

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?

Front-loaded with the return contents, and every clause (row cap, ordering, never-full-list, download_url, 'Free') carries information. The first sentence is a long run-on that stacks five facts into one breath, which slightly hurts 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, the description does the work of describing the return shape (totals by result/reason, risk flags, sample rows, download_url) very well. It leaves one gap: what happens if the job is not yet complete or the list_id is invalid — the only failure mode an agent might hit.

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?

Only one parameter (list_id) with 100% schema description coverage that already maps it to create_bulk_job. The description adds no format, range, or edge-case meaning 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?

Specific verb (summarize/total) plus resource (completed bulk job results, by result and reason) plus the exact return payload: counts, risk flags, capped example rows, download_url. The clause 'Never returns the whole list' cleanly separates it from get_bulk_csv and get_bulk_status.

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 phrase 'completed bulk job' implicitly scopes usage to post-completion and the sibling get_bulk_csv covers full downloads, so the boundary is inferable. It also gives a direct instruction ('ALWAYS give the user the download_url link'), but never explicitly says to use get_bulk_status while the job is still running or names get_bulk_csv as the alternative.

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