spatial_assess_environment_coherence

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

With no annotations provided, the description carries the full burden, and it does so well. It explicitly declares the operation is 'read-only' and discloses important behavioral invariants: hard failures are never averaged away, and inferred facts never become observed scene truth. It also details what the assessment checks, giving the agent a clear model of behavior beyond the bare schema.

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 front-loaded with a one-sentence summary, then a KB pointer, a compact example, and a dense but relevant list of evaluation dimensions. It is somewhat long, but each section earns its place for a complex assessment tool. The mismatched example reduces structural quality slightly.

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 output schema exists, so return-value documentation is covered. However, the tool has a 0% schema-description coverage, a misleading example with wrong parameter names, and no usage routing against the large set of spatial_* siblings. An agent has strong behavioral detail but cannot reliably determine argument format or when to choose this tool over alternatives.

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 description must compensate. The prose conceptually maps 'revision-bound scene facts' to scene_context_json and 'explicit design intent' to design_intent_json, but the example uses 'composition_plan_json' and 'validation_result_json', which do not match the schema's required parameter names. This is actively misleading and leaves the agent without reliable guidance for constructing the arguments.

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 specific verb and resource: 'Assess whether an environment is spatially and compositionally coherent.' It then enumerates the concrete dimensions checked (support, circulation, clearances, landmarks/sightlines, functional zones, material families, ecological rules, physical scale cues), which clearly differentiates it as the coherence-assessment tool among the many spatial_* siblings.

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 description implies usage context through phrases like 'revision-bound scene facts' and 'explicit design intent' and points to a knowledge-base section, suggesting it is used during world-building assessment. However, it never explicitly states when to use this tool versus alternatives such as spatial_analyze_room or spatial_validate_placement, and provides no when-not-to-use guidance.

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