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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds value beyond that: conflicts return the current montage (optimistic concurrency behavior), clip numbers are resolved against base_revision before the batch, and the call is free (no credits) – all non-obvious operational facts. It still does not describe what a successful edit returns or whether the batch is atomic.

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?

Five short sentences, each carrying a distinct rule, with the core purpose and the concurrency constraint front-loaded. It is terse to the point of being telegraphic ("Free."), but nothing is padding.

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 destructive, non-idempotent batch operation over a large nested oneOf schema with no output schema, the description covers the concurrency model and one key constraint. It leaves out what each op kind does, the size caps, and what the response contains on success versus conflict scenarios beyond the one sentence.

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, and it partly does: it explains base_revision's snapshot semantics and the mutual exclusivity of replace_clips. But it says nothing about montage_id format, the other op types (add/remove/move/update_clip/update_montage), or the array limits (max 30 ops, max 10 replace clips).

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?

"Change a saved montage with one batch" gives a specific verb (change) and resource (saved montage) plus the batching scope. It separates the tool from create_montage implicitly by requiring an existing montage, but it never names a sibling or explicitly contrasts with update_montage_proposal or read_montage.

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?

It supplies a prerequisite ("Read read_video_guide before you plan a video") and a hard constraint ("replace_clips must be the only operation"), which is real routing guidance. However, it never states when to choose edit_montage over create_montage, propose_montage, or update_montage_proposal, so the choice among siblings is left to inference.

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