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

Annotations declare readOnlyHint=false and openWorldHint=true, so the write/external-cost profile is partly covered. The description adds one genuinely useful behavioral rule — that videoType is supplied by the API and must be omitted — but says nothing about generation latency, async task handling, or that results are retrieved elsewhere (nexscope_media_task_result), which matters for a long-running generation call.

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?

Two short sentences with no filler; the input modes come first and the divergence from the standard request shape is flagged second. Slightly clipped phrasing ('The model is fixed by this API') costs a little clarity but nothing is wasted.

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 9 parameters and no output schema, the description covers input modes and one request constraint but leaves the caller uninformed about what comes back (task handle?) and how to obtain the finished video. Adequate to invoke correctly, not complete enough for a long-running generative 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?

Schema coverage is already 100%, so the baseline is 3. The description goes beyond the schema by explaining how parameters combine into distinct modes: imageUrl alone as a first frame, imageUrl + lastFrameImageUrl for first/last, or imageList with up to 2 reference images — a relationship the flat schema does not spell out.

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 (generate) and resource (a Kling 2.6 video) plus the three input modes (first frame, first/last frames, up to 2 reference images). It names the model, which is the main differentiator against the many sibling video generators (wan_2_6, seedance_2_5, kling_3_omni), but it never explicitly contrasts itself with those siblings.

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 description enumerates supported input modes, which implicitly tells the agent what inputs are valid, and adds a hard constraint that videoType must not be sent. It gives no guidance on when to pick Kling 2.6 over the other video-generation siblings, nor on required assets (public URLs, first frame vs reference images).

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