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

Annotations declare the mutation flags (readOnlyHint false, destructiveHint false, idempotentHint false). The description adds value beyond these: 'Costs no credits; uses account storage' and the get_generation wait hint, plus the non-destructive 'save as a new clip' framing. Lacks detail on failure modes or auth, keeping 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?

Purpose is front-loaded in the first sentence, followed by short, purposeful clauses. Slightly dense with multiple topic shifts (accurate flag, units, alternative tool, cost, waiting) but no wasted sentences.

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?

Output schema exists so return values need not be described. The description covers cost, storage impact, the waiting mechanism via get_generation, and the audio alternative, leaving only the source parameter's structure unaddressed.

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 0%, so the description must compensate. It explains accurate (re-encode vs keyframe copy) and the seconds units for start_seconds and duration_seconds, but never explains the source parameter's upload vs generation variants.

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 one stretch of an owned video as a new clip') and explicitly distinguishes itself from the sibling trim_audio ('a sound is trim_audio'). An agent can identify the operation without opening the schema.

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?

Gives a clear conditional ('Set accurate true to re-encode an exact window for seamless adjacent cuts') versus the default keyframe copy, and routes audio work to trim_audio. No explicit when-not guidance for the general case, but the key decision is covered.

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