navigation_manage

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

With no annotations, the description carries the behavioral burden and does provide useful traits: setup operations happen 'in one undo action', agents are attached 'under character/enemy node', and bake operations 'trigger in-editor baking'. It does not disclose prerequisites, repeated-call side effects, thread/blocking behavior, or error conditions, leaving gaps for an agent.

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 scannable and front-loaded, using a compact operation list with a one-line summary for each op and the canonical call shape at the end. It is longer than minimal, but the length is justified by six distinct operations and their parameter lists; no filler is present.

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 tool exposing six operations with no annotations, the description covers the key invocation details: op names, parameters, defaults, and canonical call shape. Because an output schema is present, return value details are not needed; remaining gaps are mainly prerequisites and side-effect detail rather than call syntax.

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?

Even though the input schema has 0% description coverage, the description lists full signatures and defaults for every op, such as node_path, agent_name, radius, max_speed, path_desired_distance, and target_desired_distance. This adds substantial meaning beyond the bare op enum, although a few parameters (e.g., polygon, parsed_geometry_type) lack detailed value/format semantics.

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 opens with a clear scope, '2D and 3D Navigation and Pathfinding', and enumerates specific operations (setup_region_2d, attach_agent_2d, bake_2d, etc.) with concrete resources. It is unambiguous about what the tool does, though it never explicitly contrasts itself with sibling tools such as nav_query_manage or path_manage.

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 per-op summaries provide implied guidance: use setup_region_2d for 2D regions, attach_agent_2d to attach agents, bake_2d for baking, and the 3D equivalents for 3D work. There is no explicit when/when-not guidance or mention of alternatives, so an agent must infer selection criteria from the operation names.

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