compose_logs

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

Annotations indicate read-only/non-destructive behavior. The description adds valuable behavioral context: 'never follows' (no streaming), explains the 'truncated' field, and notes a cap on output size (MAX_CLI_OUTPUT_BYTES), which significantly enhances transparency.

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 concise and well-structured, using a clear bullet-point list for parameters and a separate line for the return type. Every sentence provides value, and there is no redundancy or fluff.

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 an 8-parameter tool with no output schema and 0% schema coverage, the description covers all parameters, return type, and behavioral constraints (bounded fetch, truncation). It is fully self-contained and leaves no significant gaps.

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?

With schema description coverage at 0%, the description fully compensates by explaining each parameter's purpose, default values, and constraints (e.g., tail default 200, 'all' capped, since/until formats). This provides essential context beyond the bare schema.

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 tool's purpose: 'Fetch a bounded slice of logs from a compose project (never follows).' It uses a specific verb and resource, and the 'never follows' note helps distinguish it from sibling tools that may stream logs.

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 parameter details and return type but does not explicitly guide when to use this tool over siblings like container_logs or service_logs. The 'never follows' implies it's for bounded fetches, but there is no direct comparison or exclusion criteria.

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