rlm_orchestrate

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

With no annotations, the description reveals the multi-step process (scan, search, load) and that it combines search intelligence with raw access. This provides useful behavioral context beyond a simple operation, though it does not cover all side effects or permissions.

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 two sentences, efficiently stating purpose and listing steps. No extraneous information; every sentence earns its place.

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?

Despite a clear multi-step structure, the description omits the output format or how results are combined. For a tool with no output schema, this leaves the agent guessing about the return value. The interaction between steps and the final output are unclear.

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 75%, with three of four parameters described. The general description adds no parameter-specific meaning beyond the schema. The schema already describes each parameter adequately, so the description adds minimal value for parameter understanding.

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 performs multi-round context exploration in a single call, listing three specific steps (section scan, ranked search, raw file load). It distinguishes from siblings like rlm_search and rlm_read by combining search and raw access.

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 for multi-step exploration requiring both search and raw content, but does not explicitly state when not to use or provide alternative tools. The context among siblings suggests it is for comprehensive single-call exploration.

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