session_diff

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered; the description adds value by disclosing that mark=True writes an internal snapshot and that a single 'last mark' is retained. It does not say whether that mark survives across sessions or is overwritten silently, nor how large diffs are reported. Useful beyond the annotations but not rich.

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?

Front-loaded with the core purpose, then the two mark modes as a parenthetical, then the tracked-scope list. The enumeration of diffed categories is long but each item conveys real scope information. Slightly dense in a single sentence but no filler.

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?

With one optional boolean, an output schema present, and annotations covering safety, this is close to fully specified; the agent knows what to call and what it will cover. The remaining gap is lifecycle of the mark (overwrite, persistence, error when no mark exists), which matters because the two-step workflow depends on it.

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 0% — the single parameter has only the bare title 'Mark' — so the description carries the full burden and does. It defines both branches precisely (True records current state; False compares now against the last mark) and supplies the operational timing ('do it before an edit').

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?

The description uses a specific verb and resource ('See what changed in the open set') and enumerates exactly what dimensions are diffed (added/removed/reordered, devices, clips, faders, mute/solo, groups, returns, locators, tempo). It is clear what the tool does, but it never names the near-siblings als_diff, get_session_snapshot, or save_mix_snapshot, so an agent must infer the distinction itself.

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 gives explicit mode-level guidance: mark=True records state and should be done 'before an edit', mark=False compares to the last mark. That is a concrete when-to-use rule for both branches. It stops short of stating when this is preferable to alternatives such as als_diff or get_session_snapshot, and does not warn what happens if no mark exists yet.

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