ensemble_read

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

With no annotations, the description carries the full burden. The verb 'Read' explicitly signals a non-destructive operation, and the phrase 'in one call' discloses atomic behavior. It also hints at internal logic by including 'what has changed recently' and linking to the session listing fallback (via schema). It doesn't discuss error handling or auth, but the read-only nature is strongly implied.

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 a single, well-structured sentence with a front-loaded verb and resource, followed by a colon and a comma-separated list of content items. Each listed item earns its place and collectively conveys the full scope without redundancy or filler. It is both concise and information-dense.

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 that there is no output schema, the description appropriately enumerates the return content in detail (key, tempo, voices, parts, version, changes). It also conveys the primary use case of preparing to write. It does not specify the output format or how the version should be interpreted, which is a minor gap, but overall it provides a solid mental model.

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. The main description adds value by connecting parameters to usage: 'bars' to 'the bars you are about to write', 'agent' and 'voice' to 'your own part' and 'the version to write against', and 'history' to 'what has changed recently'. This enriches the schema's brief descriptions and clarifies how each parameter shapes the read operation.

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 clearly states the verb 'Read' and the resource 'session', then enumerates a comprehensive list of specific data it retrieves (key, tempo, metre, form, voice assignments, parts, version, recent changes). This explicit scoping distinguishes it from sibling tools like ensemble_status or ensemble_log, which likely focus on narrower aspects. The phrase 'in one call' further emphasizes its consolidated role.

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 provides clear situational context by mentioning 'the bars you are about to write', implying it is intended for use before composing. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of offering exclusions or direct comparisons. This matches the criterion of clear context without explicit alternatives.

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