fx

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

With no annotations, the description carries the full burden. It discloses that operations are undo-block wrapped, supports dry_run, that fuzzy resolution works against the installed-plugin cache, and that dry_run add requires exact fx_name. It also warns about live recording context. Missing: whether any operation is destructive or reversible beyond undo, permission requirements, or error behaviors beyond the fuzzy resolver note.

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-loads the action enumeration well, but the description is bloated with repetitive anti-pattern warnings ('Do NOT precheck', 'do NOT hedge', 'do NOT narrate a plan') that could be consolidated. The all-caps emphasis ('JUST RUN add IN ONE CALL') feels like shouting and harms readability. Several sentences do not earn their place relative to the core purpose.

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?

Given 13 parameters, no output schema, and no annotations, the description provides essential context: undo-block wrapping, dry_run semantics, fuzzy resolution behavior, master track targeting, and live-recording awareness. It is missing explicit guidance on fx_index/fx_scope/to_index usage and error conditions for multi-track matches, but covers the most critical behavioral aspects for an agent to invoke 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 coverage is 69%, so the schema documents most parameters. The description adds meaning for dry_run (preview, and the special case that dry_run add needs exact fx_name, no fuzzy resolution) and for track targeting (track:"master" targets master). However, other parameters like fx_index, fx_scope, to_index, and track_contains are left entirely to the schema. The description adds value but does not fully compensate for the 31% gap.

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 specific verb+resource (FX chain operations) and enumerates the four actions (add, remove, bypass, move). It distinguishes from siblings like scan_fx by explicitly telling the agent NOT to use scan_fx for prechecking. However, the description is cluttered by anti-pattern instructions, which dilute the core purpose statement.

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?

Explicitly states when to use this tool (to add a plugin, just run add in one call) and when not to use alternatives (do NOT precheck with scan_fx). Directly addresses the common failure mode of prechecking and hedging. This is exactly what usage guidelines should do.

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