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

Beyond the idempotentHint and destructiveHint annotations, the description reveals that the response snapshot is not authoritative verification and that a get_session call is mandatory next. It also clarifies operation-specific scopes, e.g., set_steps never replaces a track or session and set_track_instrument preserves pattern/mix/timing/name. This substantially enriches the annotation flags with actionable constraints.

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 description is six dense, well-ordered sentences: purpose, follow-up protocol, snapshot caveat, supported operations, and two clarifying operation semantics. Every sentence adds value beyond the schema, and the most critical constraint (next call must be get_session) appears early.

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?

The tool has high complexity with five edit variants, but the schema richly documents each variant. The description fills the remaining gap by explaining the response snapshot's non-authoritative nature and the required follow-up call, which is sufficient for safe usage despite the absence of an output schema.

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?

The schema already covers all parameters at 100%, providing a strong baseline. The description adds behavior-level meaning for edit variants, such as 'set_steps changes only the named steps; it never replaces a track or session' and 'set_track_instrument replaces only a track's sound source,' which helps the agent infer parameter effects beyond raw schema constraints.

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?

The description opens with 'Make one narrow, retry-safe edit to an existing collaborative session,' a precise verb+resource+scope statement. It lists the five supported operations (add_track, set_track_instrument, set_track_pan, set_steps, set_tempo), clearly distinguishing this mutation tool from siblings like get_session or create_session.

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?

It explicitly states when to use this tool ('edit to an existing collaborative session') and provides an explicit follow-up protocol: 'After every attempt, the next Keyboardia call must be get_session for the same session.' It also gives a when-not directive ('do not make another edit or finish from it') and names the alternative read tool ('Read with get_session next').

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