song_read

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

No annotations are provided, so the description carries the full burden. It does add one genuinely useful behavioral fact: the result reflects the last save, not unsaved edits, which separates it from live_* tools. However it says nothing about file-not-found/ambiguous-match behavior, permissions, or how a title match is resolved beyond the schema's 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?

Two sentences, no filler, and the return-content inventory is front-loaded before the staleness caveat. The enumeration is dense but earns its place since no output schema exists to describe the payload.

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 no annotations and no output schema, the description usefully enumerates return contents and flags staleness. The remaining gap is the lack of explicit routing against song_list/live_song and of error/ambiguity behavior, but for a read-only inspection tool this is largely complete.

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 100% and each parameter (song, track, detail enum) is already documented with its semantics in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

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 (Read) and resource (a Studio One song from its .song file) and enumerates the exact payload: tempo, time signature, markers, arranger sections, tracks/takes/clips, mixer channels, media files. This clearly distinguishes it from live_* siblings that query a running session rather than a saved file.

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?

The description implies usage (read a saved .song file) but never explicitly says when to choose it over song_list, song_history, or the live_song/live_tracks family. The stale-vs-live distinction is implied by the last sentence rather than stated as routing guidance.

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