set_recast_navmesh_settings

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

Annotations already declare idempotentHint=true and destructiveHint=true; the description reinforces the idempotence ('partial/idempotent') and adds real context the annotations do not carry: only supplied params are applied and all numerics are clamped server-side before use. It also exposes the return contract (requires_rebuild, rebuilt, applied map). It does not explain the destructive side (what existing nav settings are overwritten or how reversible an applied change is), so not a 5.

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?

Front-loaded: the core action and the partial/idempotent semantics come first, followed by the return shape. Given the absence of an output schema, the Returns line earns its place. Slightly dense parenthetical, but no wasted sentences.

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?

With no output schema, the inline Returns contract compensates well, and the partial/clamping semantics cover the main invocation ambiguity (units, validation, what a rebuild flag does). Gaps remain for a destructive setter: no mention of required edit context/permissions, no relationship to sibling rebuild_navigation, and no note on interactivity of the synchronous Build().

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%, with each parameter documented including clamp ranges (1..1024, >=300, <=89), so the schema does the heavy lifting. The description adds only the generic claim that numerics are clamped server-side and unprovided fields are untouched, with no per-parameter meaning beyond the schema. Baseline 3 is appropriate.

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 verb+resource with scope: 'Configures generation settings on the editor world's default ARecastNavMesh'. The agent can tell it sets navmesh generation parameters, distinct from the getter get_recast_navmesh_settings. However, it never names the obvious siblings (get_recast_navmesh_settings, rebuild_navigation, diagnose_navmesh), so sibling differentiation is left to inference.

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?

Implies usage through 'partial/idempotent; only provided params are applied', which tells the agent it can call it with any subset of fields. But it gives no explicit when-to-use-vs-alternative guidance: nothing says when to use this instead of rebuild_navigation, or that get_recast_navmesh_settings is the read counterpart. Usage is inferred, not stated.

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