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

The description's most valuable addition is 'Results differ on every call,' which explains the meaning behind the idempotentHint=false annotation rather than restating it. Beyond that it adds little: no statement of return shape, ordering, or what happens when filters match nothing, which matters for a sampling tool.

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?

Two short sentences, front-loaded with the operation and then the intent; no filler. It could be tightened slightly by folding the non-determinism note into the first sentence.

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?

A simple read-only tool with fully described parameters and annotations covering safety, so the burden is light. However, in the absence of an output schema the description says nothing about what a returned reference contains or what an empty result looks like, leaving a real gap.

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 coverage is 100%, so the enums, defaults, bounds (1-10) and AND-semantics of tags are already fully documented in the schema. The description only gestures at category/tags and never mentions lang or count, so it adds nothing beyond the schema.

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 a random selection of references') and adds the scope 'optionally within a category or tags.' The random-selection framing implicitly separates it from get_references/search_references/similar_references, but no sibling is named, so differentiation must be inferred.

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?

'Suits open-ended inspiration' implies a use case but gives no explicit when/when-not guidance and never mentions the filtered-listing siblings as the alternative when the agent needs deterministic results.

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