Get a Dare generation

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

Annotations already carry readOnlyHint, idempotentHint, and destructiveHint=false, and the description's 'Read-only' line is consistent with them. It adds meaningful context beyond annotations: the long-running nature of video jobs, the blocking semantics of wait_seconds, and the notion of terminal statuses. It does not disclose edge behavior when wait_seconds expires while a job is still pending, which keeps it from a 5.

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?

Three sentences (~70 words) with zero filler: the opening sentence states function and return contents, the second declares read-only, and the final sentence covers when and how to poll. The most decision-relevant information (statuses, return contents, polling loop) is front-loaded.

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 to explain return values, the description directly covers the return surface (status, credits, URL). Combined with the annotations' safety profile and the fully documented schema, an agent can determine whether to call, how long to wait, and how to interpret results. Minor gaps — behavior on unknown ids and on wait_seconds timeout — keep it short of a 5.

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 description coverage is 100%, so the schema already documents all three parameters well, giving a baseline of 3. The description earns an extra point by adding client-specific sizing guidance for wait_seconds (45 for desktop apps, 300+ for Claude Code) and grounding generation_id's provenance in the dare_generate_* tools.

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 names a specific verb ('Fetch'), a specific resource ('one generation by id'), and enumerates exactly what is returned (status, credits charged, output asset URL). The 'one... by id' framing unambiguously distinguishes it from the sibling dare_list_generations without any inference.

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 explicitly anchors when to use this tool: 'Poll this after dare_generate_video,' with a concrete latency expectation (5–15 minutes) and a clear polling loop ('call again until status is terminal'). However, it never states when-not to use it or names an alternative tool for listing or other scenarios, so it falls just short of the explicit exclusion bar.

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