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

Annotations only say non-readOnly, non-destructive, non-idempotent and open-world; the description adds the operational facts an agent actually needs beyond that: async job semantics with a 30-90 s wait, a pre-signed zip URL that expires in 24 h, credits that are spent even if the job is abandoned, that a running build cannot be stopped, and that only a queued job is refunded. It also discloses secondary behavior such as video re-encoding to 720p, the video appearing only as a muted track in REAPER/Logic, and Ableton projects being built without video.

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?

The opening sentence front-loads the deliverable and the source/target choices, so scanning yields the essentials quickly. It is dense — the run of clauses about cues, tempo maps and reference tracks in one sentence, plus a long trailing paragraph on cancellation and refunds, costs a little readability, but almost every clause carries distinct information.

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 15-parameter, nested, async rendering tool with no output schema, the description covers the workflow, the return artifact (pre-signed zip named <name>_session.zip) and the failure/cancel economics, which is nearly everything an agent needs. The only gap is that it says nothing about the shape of an error or partial-failure response, which matters for a job that can spend credits and be discarded.

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 100%, so the baseline is 3, but the description adds real meaning the schema does not carry: stems URLs may be result links used as-is, cues replaces from_job/mix_job/stems and caps at 12 cues with bar-1-on-a-bar-line joining, target defaults to logic, and mixgraph applies only gain_db and pan (its EQ, compression, reverb and rides are discarded). The idempotency_key and session_beats interplay is left to the schema, which keeps this off a 5.

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 and deliverable ("Build a native DAW PROJECT from stems") plus the concrete artifacts (one audio track per stem from bar 1, optional MIDI tracks, on your tempo) and the three output formats (.logicx, .als, .rpp zipped). It is clearly separable from siblings like doseedo_render_score and doseedo_separate_stems because it consumes their output rather than producing audio.

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 three explicit entry paths with the condition selecting each: pass from_job plus a doseedo_render_score job_id, pass raw stems [{name, audio_url}] from renders/separations, or add mix_job after doseedo_mix. It also names the mandatory follow-up (doseedo_wait_task ~30-90 s) and explains the cues alternative for multi-cue films, so an agent never has to guess which parameter set applies.

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