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

Annotations only declare the safety profile (not read-only, destructive, open-world, not idempotent); the description adds the operational facts an agent actually needs: tokens are spent and priced off the new segment's model/duration/resolution, an external URL consumes one media-ingest slot (quote and create from the same URL), and a reused idempotency_key REPLAYS rather than creates. It also discloses that the card was already opened and specifies a wait protocol, none of which is inferable 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?

Front-loaded correctly: purpose and return value in sentence one, then WHEN, card, wait, cost, tokens, idempotency in labeled blocks that are easy to scan. Some bloat remains in capitalized imperatives and the split COST / SPENDS TOKENS sections, and phrases like "again at once while `terminal: false`" are compressed to the point of ambiguity.

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?

For a costly, open-world, non-idempotent mutation with 9 params and no output schema, the description covers every decision the agent must make: model discovery, pricing and approval protocol, URL ingestion cost, idempotency hazard, UI card state, wait protocol and the no-card fallback of handing over the URL.

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% and several param notes are near-duplicates of the schema (duration as NEW segment length, aspect_ratio not guessed). But the description adds constraint-level meaning the schema lacks: `model` must be one that can start from an image, `prompt` should describe what happens NEXT or you get a repeat of the source, and the same-URL ingest-slot rule spans two parameters.

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?

First sentence gives a specific verb, resource and distinctive mechanism: generates a NEW segment continuing from the video's final frame, returns the job id immediately, and the result is the source clip with the segment joined on. That last clause cleanly separates it from generate_video, edit_video and reshot_video without naming them.

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?

An explicit WHEN clause names the user intents that trigger it (extend, continue, lengthen, "what happens next"), plus prerequisites (call list_models first; only image-start models accepted) and an explicit prohibition (do not call show_generation for this job). It also routes post-call behavior to wait_for_generation and away from get_* polling, which is real alternative-selection guidance.

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