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

Annotations declare non-read-only, non-destructive, non-idempotent. The description is consistent, adding that the output is a NEW image result (so nothing existing is destroyed) and the endpoint. It does not explain what happens on repeat calls (idempotentHint=false implies duplicates) or auth requirements.

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?

One tight sentence plus a UI anchor phrase; the action and output are front-loaded with no filler. Slightly terse rather than padded.

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 mutation with no output schema that produces a brand-new artifact, the description never indicates what is returned (e.g., the new image result id) or how the new frame relates to the source result. Combined with the undocumented required parameter, an agent lacks enough to use it confidently.

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 only 50% and the description names no parameters at all. It says 'a still frame' without clarifying which frame, so the caller learns nothing about timestamp_seconds (last frame by default) or the required generation_result_id beyond what the schema shows.

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 and resource: 'Save a still frame of a video result as a new image result', plus the underlying route. It is clearly distinguishable from siblings like mcp_save_retouch or mcp_generate_clip, though it doesn't explicitly name a sibling.

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 phrase 'The result viewer's Save frame' anchors the tool to a known UI action, implying when it applies. However, it gives no conditions for choosing it over alternatives and no exclusions or prerequisites, leaving usage largely inferred.

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