preview_routing

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

With no annotations, the description carries the full burden; it does disclose the most important behavioral fact, that nothing is dispatched, which signals a safe read-only preview. It says nothing about whether the preview calls any external provider, the cost/latency of previewing, or any prerequisites, so it is not fully transparent.

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?

One front-loaded sentence with no filler, and the scope qualifier ('without dispatching') is placed where it will be read. It is efficient, though the terseness leaves no room for any parameter cue.

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?

An output schema exists, so return values need not be explained here. But a four-parameter tool with zero schema descriptions and three 'auto'-defaulted routing knobs is not adequately covered by a single sentence; the agent cannot tell what the optional parameters do or how they shape the preview.

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 0% across four parameters, and the description never mentions a single one. The meanings of task_kind, difficulty, and target_harness, and what their 'auto' default does, are entirely undocumented in both the schema and the description.

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 gives a specific verb ('Preview'), resource ('the routing decision'), and input ('for an objective'), and the phrase 'without dispatching it' implicitly marks the difference from dispatch_task. It stops short of naming a sibling explicitly, so the differentiation is inferable rather than stated.

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?

'without dispatching it' implies a dry-run/inspection use case before real dispatch, which is genuine usage context. However, there is no explicit when-to-use or when-not-to-use rule, and no sibling is named (dispatch_task, parallel_dispatch, discover_harness_models) to route the agent elsewhere.

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