navmesh

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

The description notes that 'clear' removes all NavMesh data and 'bake' generates the NavMesh, implying destructive potential. However, it does not explicitly warn about irreversible actions or required permissions. With only a readOnlyHint=false annotation, the description should provide more safety cues.

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 relatively concise but uses a bullet list that is easy to scan. However, it could be better structured by grouping read vs write actions or adding a brief usage note. It is not excessively long but lacks optimal organization.

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 (21 parameters, 13 actions, no output schema), the description is insufficient. It does not explain how parameters are action-specific, nor what return values or side effects to expect. The agent would need to infer parameter-action mapping from parameter descriptions alone.

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?

All 21 parameters have descriptions in the input schema (100% coverage), so the schema carries the semantic load. The description adds no extra meaning about how parameters relate to actions, e.g., x,y,z are only for sample_position. Baseline 3 applies as the description does not detract.

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 'Manage Unity NavMesh navigation system' which clearly indicates the tool's domain. It lists 13 specific sub-actions, giving a good overview. However, the overall purpose is somewhat generic and could be more precise about what managing NavMesh entails beyond the listed actions.

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?

There is no guidance on when to use this tool versus other siblings like physics or terrain, nor when to choose one action over another. The description simply enumerates actions without context for selection or prerequisites, leaving the agent to infer usage.

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