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

With annotations covering the safety profile (readOnly=false, destructive=false), the description adds real behavioral detail beyond them: report 'writes nothing', re-running 'replaces earlier steps', and 'off' removes them all, so reversibility and mutation semantics are clear. It is silent on prerequisites such as whether a prior analysis/render pass is required and on any permission or scope failure modes, which keeps it short of 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?

Dense and long, but the load-bearing facts are front-loaded (scope, then 'report FIRST', then the mechanics and the when-to-use caveat). Some clauses are expendable or repetitive ('This is not an expressive zoom and not a rule' restates 'never a default'), and the single run-on paragraph with nested parentheticals hurts scannability.

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 four-parameter, no-output-schema tool of high complexity, the description supplies the missing return information ('lists every same-shot jump cut — how visible the jump is, what already covers it, the hook and stutter flags, and the options'), the parameter semantics, and the scope/mutation model. An agent has everything needed to pick a mode and call it correctly.

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 only 25% (project_id alone is documented), so the description carries the burden and does: mode's three values are each defined, step gets a range and default ('0.10-0.15, default 0.12') plus a failure threshold ('under ~10% a step stutters'), and `at` gets a format and purpose ('[program seconds] names cuts you saw pop instead'). Only project_id is left to the schema, and the schema documents it.

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?

Names a specific action on a specific resource (conceal jump cuts via framing steps) and explicitly distinguishes itself from neighbors: 'This is not an expressive zoom' separates it from add_zoom/add_zoom_path, and 'a bare jump cut is fine... only when the render shows cuts popping' separates it from a blanket transition tool. The mode vocabulary (report / scale_step / off) makes the three behaviors legible 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 an explicit workflow ('mode=report FIRST'), an explicit trigger condition ('use it only when the render shows cuts popping — typically a static archival or single-camera talk tightened by pause removal'), an explicit ordering constraint ('after the cut is final'), and enumerates alternatives ('leave it, move a graphic change onto it, restore or re-cut the join, or a step'). It even states when NOT to use it ('never a default', 'not a rule').

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