bake_navmesh

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

With no annotations, the description carries the burden and does disclose two useful behaviors: the operation waits for a bounded amount of time so it shouldn't hang, and it defaults to preview mode. However, it doesn't say whether baking modifies the stage persistently, whether preview avoids all side effects, or how failures or timeouts surface. That missing side-effect and error context keeps this at a 3.

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 sentence with no filler; verb, resource, wait behavior, and preview default are all front-loaded. It is as compact as possible while communicating the core behavior.

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?

The definition is adequate as a high-level summary, but incomplete for a tool with 4 parameters and no annotation safety profile. It doesn't explain preview semantics, the meaning of command_id/idempotency_key, or failure behavior, despite having an output schema to describe results. An agent would need to infer or experiment to call it correctly in a non-default scenario.

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%, so the text must explain the 4 parameters; it only loosely maps 'bounded wait' to max_frames and re-states the preview default. command_id and idempotency_key are completely unaddressed, so an agent cannot know how to set them or why they exist.

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 names a concrete operation ('Bake'), a specific resource ('current stage NavMesh'), and key behavioral qualifiers (bounded wait, preview by default). This makes it easy for an agent to identify what the tool does. It doesn't explicitly call out sibling tools, so it doesn't fully earn the top score.

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?

No guidance is given about when to bake versus checking status or using other navigation tools; there is no reference to get_navmesh_status or prerequisites such as having a valid stage or agent. The 'preview by default' hint implies a safe/test usage but does not state when to set preview to false. This leaves usage decisions to the agent.

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