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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive), and the description is consistent with them ('Read-only'). Beyond that it discloses behavior no annotation carries: the note inline/omission budget (≤200 notes, else note_count + notes_omitted:true), track-level pagination via `truncated` + `next` with the exact resume args, the 'never cut mid-JSON' guarantee, the sync.live_edits flag answering 'will an edit reach Logic now?', and markers being absolute beats from bar 1.

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 payload, then budget, then next steps — a sensible order. It is a dense run-on with heavy parentheticals that hurts scannability, and the long inline field enumeration partially duplicates the doseedo_edit_ops_reference call it already points to, but nearly every clause carries usable 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?

No output schema exists, so the description carries full burden for a very complex return, and it does: top-level shape, id conventions, budget/degradation behavior, pagination contract, and the sync freshness signal. An agent can call it, interpret a truncated result, and continue without another discovery call.

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 cross-tool meaning the schema cannot: `i` is what edit_midi_notes selects by, param_id is required by set_device_param, ch_b_… denotes sends/output, and the include_* flags are framed as interlocking budget fallbacks with the pagination path. That is genuine semantic value over the field definitions.

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+resource ('Read a DAW session') and immediately frames it as 'the arrangement an agent edits against', then enumerates the exact payload (tracks with wire ids, regions, mixer, plugins, buses, tempo_map, sync). It also positions itself against siblings: it produces ids consumed by doseedo_edit_session and doseedo_render_midi. An agent can tell this is the read-state entry point, distinct from doseedo_list_sessions, without opening a schema.

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?

Clear routing context: pass returned ids to doseedo_edit_session, a track_id to doseedo_render_midi, and consult doseedo_edit_ops_reference for the field map. It also gives concrete usage triggers for the knobs ('pass include_notes:true with tracks:[ids] for a track's notes'). No explicit when-not-to-use condition is stated, so not quite a 5.

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