find_stalled_downloads

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the exclusion of paused/queued items, the semantics of the min_hours grace period, and the fact that it flags client errors and metadata-less magnets.

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?

The stall conditions are front-loaded and the follow-up pairing plus examples come last. It is dense but each clause enumerates a distinct detection rule; the example list is slightly redundant given the already-explicit criteria.

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 an output schema present, return values need not be explained. The description covers detection criteria, exclusions, parameter behavior, and the natural next action, leaving no gap for an agent deciding whether and how to call it.

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 the baseline is 3. The description adds meaning by tying min_hours specifically to the no-progress check ('after min_hours — still at 0%'), clarifying that the threshold does not gate the other stall conditions.

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 specific verb+resource (find downloads) and enumerates the exact conditions that qualify as 'stalled' (client-reported stall, no connections/seeds, error, 0% after min_hours, no activity, no metadata). This is precise enough to distinguish it from siblings like get_queue and find_orphan_downloads.

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 specifies when-not (paused or queued items are not reported) and names a concrete follow-up alternative, remove_from_queue(blocklist=true), plus example user utterances. It stops short of explicitly contrasting against get_queue or find_orphan_downloads as the tool to pick instead, so it is clear but not fully routing.

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