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

Annotations already declare not read-only, not destructive, not idempotent, closed-world. The description adds genuinely useful context beyond that: no rendering cost, no charge, ordering semantics, and version-based scoping. It still omits what happens to a prior selection, whether the call blocks, and error behavior for the version mismatch implied by the non-idempotent hint.

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 and constraints are front-loaded, which is good, but the trailing raw JSON argument dump largely duplicates the input schema and adds little for an agent that already receives the schema. Roughly half the text is redundant with structured fields.

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 non-read-only, non-idempotent mutation with nested required params and no output schema, the description covers purpose, cost, and ordering but leaves result behavior, prior-selection semantics, and the version contract unexplained. Adequate but with visible gaps.

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% and both top-level params are required nested objects. The description partially compensates: 'up to 12 ... in order' explains job_ids bounds and ordering, and 'Uses the editing version' gestures at the version field. However, it never explains what the version integer is for (likely concurrency/optimistic locking) or that job_ids are video job identifiers, so the 0% coverage is only partly offset.

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 (select) and resource (completed videos owned by the authenticated account), plus the scope constraint of up to 12 and ordering. It is clear what the tool does, but it never names or contrasts with related siblings like kelpo_start_editing, kelpo_get_editing, or kelpo_finalize_editing, so an agent has to infer where it sits in the editing workflow.

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 gives preconditions (completed videos, authenticated account, max 12) but no when-to-use guidance and no explicit alternatives among the many editing siblings. 'No rendering or charge' hints at cheap sequencing but does not tell the agent when this call is required versus skippable.

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