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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds meaningful context beyond them: that learned types/aliases originate from stored data and that 'dudas' entries are still awaiting a decision, implying a dynamic, evolving vocabulary.

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 with purpose, then scope, then return shape. Information-dense and mostly waste-free, though the inline enumeration of the return object (core/extensions/core_aliases/dudas plus relation properties) is long and slightly run-on for a description body.

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 description carries the burden of explaining return values, and it does so in useful detail (core vs extensions, aliases, dudas, and the per-type properties like inverse/functional_in_time/temporal/transitive). It stops short of showing the exact dudas entry shape, but an agent has enough to act.

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?

The tool takes zero parameters, so the baseline is 4. There is nothing further the description could add about inputs, and it correctly spends no space on them.

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 and resource ('Return the world-model vocabulary') and immediately scopes it to core entity/relation types plus account-specific learned types and aliases. This is clearly distinguishable from siblings like query_world_model, get_world_model_stats, or list_entities.

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 explains how the returned vocabulary is consumed downstream: learned relation types are usable in process_observation triples while relate_entities accepts core types only. That effectively tells the agent when the output matters, though it never states an explicit 'call this before relate_entities' trigger or when-not-to-use condition.

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