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

With no annotations provided, the description must shoulder behavioral disclosure. It reveals that known operator clusters share assignment, which is useful, but it does not state that the operation mutates state, what 'explicitly eligible' means, how idempotencyKey affects behavior, or any permission/error conditions.

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 two clauses, front-loaded with the core action. The assignment-sharing clause earns its place by adding important behavioral context without padding.

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?

For a tool with 3 required parameters, a nested assignment object, and no output schema or annotations, the description is too sparse. Missing: meaning of eligibilitySnapshot, idempotency semantics, how to specify the variant, and success/error outcomes.

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. It loosely maps to parameters ('unit' to id/subjectId, 'experiment variant' to assignment, sharing rule to agentId/cluster) but never explains idempotencyKey, eligibilitySnapshot, provenance, or parentId, which leaves the nested object largely opaque.

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 states a specific action: assigning an explicitly eligible unit to a fixed experiment variant, and adds a quirk about operator clusters sharing assignments. It distinguishes itself from assign_task by targeting experiment variants, though the term 'unit' is somewhat abstract and no sibling is named.

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?

There is no guidance on when to use this tool versus alternatives. Given many research-related siblings (create_research_run, set_research_state, record_research_observation, consent_research), the agent must infer usage solely from the word 'assign'. No exclusions or alternative conditions are stated.

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