dreamlayer_generate

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

With no annotations, the description carries the full burden and does a solid job: it discloses that it returns an event stream, may end with a question (and that's not a failure), and costs one credit per finished image. It also mentions that setting 'operation' makes execution deterministic. These are meaningful behavioral traits beyond the schema. It doesn't cover every side effect (e.g., whether edits overwrite assets), but it covers the most important and unusual behaviors.

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?

Two sentences with zero waste. The main purpose is front-loaded, and the caveats (question behavior, cost) are placed immediately after. It is concise and to the point, with no redundant phrasing.

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 the tool's complexity (7 params, multiple operations, no output schema) and the existence of sibling tools for execution and events, the description covers the essential behavioral context (event stream, question possibility, cost) but omits explicit routing to those siblings. The schema covers parameter details, so the description doesn't need to repeat them. It feels complete enough for an agent to know what to expect, though it could benefit from a pointer to dreamlayer_events for consuming the stream.

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 71%, so most parameters have descriptions. The description adds value by explaining that 'operation' can be set to run deterministically and skip interpretation, which is not obvious from the schema alone. However, it doesn't compensate for the two undocumented parameters (prompt, conversation_id), and it doesn't elaborate on how they interact with the question flow. The added value is moderate, so a 3 is appropriate.

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 states a specific action ('Generate or edit an image') and a concrete outcome ('return the resulting event stream'). It also adds an unusual behavior (may ask a question) that distinguishes it from typical generation tools. It clearly differentiates from siblings like upload or events by focusing on the generation/editing 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 implies usage (generate or edit images) but does not explicitly mention alternatives or exclusions. It doesn't reference sibling tools (e.g., dreamlayer_upload_image for uploading, dreamlayer_events for reading events) or provide conditions for when to choose this tool over others. The 'may ask a question' note hints at a workflow but lacks explicit guidance.

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