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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds substantial non-annotation behavior: long-running calls return job_id to poll via job_get, brain-gated tools error and require brain_query output re-passed as brain_context, built-in tools must be invoked directly, and local files must be hosted via file_write before use.

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?

Information-dense and largely front-loaded: the core action and the route/discover alternatives come first, followed by caveats. It is long, but for a 7-parameter gateway tool most sentences carry distinct routing, error-recovery, or precondition content rather than filler.

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 a high-complexity dispatcher with 7 params, nested objects, open-world access and no output schema, the description covers alternatives, error recovery (brain_context, job polling), preconditions (file hosting) and exclusion rules. Nothing an agent needs to call this correctly is missing.

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 description coverage is 100%, so the schema already documents tool, skill, input, backend, billing, brain_context and response_format. The description reinforces the critical top-level placement of brain_context and notes the max-4 image merge default, but it mostly restates what the schema already carries. Baseline 3 applies.

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?

States a specific action on a specific resource: dispatch a ToolRouter catalogue tool by name and skill. It explicitly draws the boundary against siblings, naming discover, route, credits_balance as NOT catalogue tools that must be called directly. An agent can distinguish use_tool from route/discover without opening the schema.

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?

Gives explicit routing guidance: prefer route when tool+skill are unknown, use discover to obtain schemas/listing first, and call use_tool only with exact tool and skill names. It also covers the job_id polling path, the file_write prerequisite for image/file URLs, and the brain_query prerequisite when a brain_context error is returned.

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