download_speech_history_items

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description usefully adds that the payload is application/zip bytes (a multi-item archive), which the annotations do not convey, but it omits auth requirements, size/batch limits, and whether re-running is safe.

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 compact sentence, front-loaded with the action and return type. The phrasing is slightly run-on ("Download History Items Returns application/zip bytes"), but every clause carries information.

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 and a filesystem-writing operation, the description should at minimum clarify what the zip contains and what output_format accepts. It does disclose the zip return type, but leaves output_format and multi-item/batch behavior undocumented, so the definition is only partially 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 only 67%, and output_format carries no description anywhere. The description merely restates the already-documented output_path behavior ("pass output_path to save them") and adds nothing about output_format or valid ID sources, so it fails to compensate for the coverage gap.

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 ("Download History Items") and adds the return format (application/zip bytes). However, it does not distinguish itself from near-siblings such as get_audio_full_from_speech_history_item, get_speech_history_item_by_id, or get_speech_history, so the agent cannot tell which history-fetching tool applies without reading schemas.

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 only guidance is "pass output_path to save them," which is a parameter note rather than a when-to-use rule. There is no statement of when this bulk-download tool should be chosen over the single-item audio siblings, nor any prerequisite or exclusion.

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