get_generation_task

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

Annotations only declare readOnly/openWorld/non-destructive, and the description adds substantial behavior beyond that: cached:true responses with remaining wait and no backend request, no retry on uncertain submissions, reconciliation via website history, and a rejection of arbitrary backend IDs. This is genuinely useful context an agent could not infer from the annotations.

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?

It is a dense wall of prose mixing polling semantics, UI/presentation instructions, and delivery formatting, with 'Do not reopen the same card' repeated for both audio and video. The core read-a-task purpose is buried behind downstream workflow rules rather than front-loaded, so much of the text does not earn its place in a getter's description.

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 compensates by naming the states that matter (completed/failed), the result shape (artifacts[].url, model, voice, consumption with credit type, duration), and the polling contract. The remaining gap is that it never states whether image-generation tasks are also served by this tool versus get_image_task.

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?

The single parameter has 0% schema description coverage (schema supplies only format/pattern), so the description carries the meaning: the handle is account-scoped, was created by this MCP, and arbitrary backend IDs are never accepted. That is exactly the semantic layer the schema lacks, though it does not describe handle lifetime or reuse.

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 states a concrete verb+resource: read an account-scoped task_handle created by this MCP, and scopes it to music/video/speech task families. It never explicitly distinguishes get_generation_task from siblings like get_image_task or get_music_entitlements-family tools, leaving the agent to guess whether image tasks route here or elsewhere.

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?

Strong operational guidance: wait poll_after_seconds (~20s) between queries, stop polling on completed/failed, concurrent calls return cached state, and route to preview_audio_task/preview_video_task once at completion. It lacks explicit when-not-to-use-this-tool guidance (e.g. which task types belong to get_image_task), so it stops short of full routing clarity.

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