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

Annotations already declare openWorldHint and non-idempotent, and the description adds valuable side-effect context: deduplication, one job per 100000 addresses, credits consumed only when the last part triggers the job. It does not cover retry behavior or what happens if a part is resent (important given idempotentHint=false), leaving a small gap.

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 dense sentence, front-loaded with the action and cap, then the terminal behavior and credit rule. Efficient, though the packed clause structure (three ideas in one sentence) is slightly harder to scan than separated points.

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?

Covers the sequencing contract, side effects, billing trigger, and points to create_bulk_job for the return shape, which compensates for the absent output schema. A brief note on failure/retry semantics for a non-idempotent append would make it fully complete.

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 coverage is 100%, so both parameters are already documented, including the 1-5000 range and the uuid format. The description only restates the 5000 cap and implies the upload_session provenance, which the schema already states — 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 ('Send the next part... of a list') and pins its scope with the 5000-address cap. It clearly distinguishes itself from create_bulk_job by being the continuation step, and even explains the terminal behavior (dedup + upload).

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?

Explicitly names the prerequisite (a list started with create_bulk_job and parts_total) and the terminating condition ('after the last part'). An agent knows exactly where this tool sits in the workflow and when to stop calling it.

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