agent_midi_preview

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

Annotations already declare readOnlyHint and destructiveHint=false, and the description adds genuinely new constraints: the file must be local and 'bounded ... under output-root' (a sandbox restriction), and metadata is 'never applied' (no side effects on the session). It stops short of saying what the preview response contains, which matters given there is no output schema.

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?

A single dense sentence with the action front-loaded and no filler. It is compressed to the point of using unexplained jargon, but nothing is redundant.

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 no output schema and 0% parameter coverage across three required params, the description should explain the track/slot addressing and what the preview reports. It only covers the read-only nature and path bound, leaving the caller unable to predict the response or fill in track/slot confidently.

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 all three parameters are required, so the description carries the full burden. It hints at a path restriction ('under output-root') but says nothing about what 'track' (string or integer) or 'slot' (0-255) mean or how they select the previewed data.

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 pair ('parse ... and preview MIDI notes') and a specific resource type (SMF/RMID files), which is enough to separate it from generic siblings like agent_preview or agent_arrange_preview. The jargon 'SMF/RMID' and 'output-root' are unexplained, but the core action is unambiguous.

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?

'preview ... metadata is reported, never applied' implies a read-only dry-run step, so an agent can infer this precedes something like agent_apply. However, no sibling is named and no explicit condition says when to use this versus agent_preview or agent_arrange_preview.

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