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

Annotations already provide readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds meaningful behavior beyond those: exact/deterministic writes, no AI generation, and concurrency protection via source_stage returning 409 when stale. It does not explicitly state that existing directions are overwritten, but 'set exactly as written' strongly implies it.

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 three short sentences with no filler. It front-loads the core action and determinism guarantee, then adds the key preconditions and concurrency behavior in the remaining 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?

For a mutation tool with no output schemaainer, the description covers the essential agent-facing aspects: what is set, how it is set, at least one field requirement, and stale-source handling. It does not fully spell out whether omitting one direction field preserves or clears the existing value, but the 'and/or' wording plus optional schema fields make preservation the reasonable reading.

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 adds useful semantics for the direction fields and source_stage, including 'at least one' and stale 409 behavior. However, it does not explain round_id, resource, or the action envelope, leaving some parameter meaning to the schema's structural constraints.

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 names a specific verb and resource: 'Set one draft round's interviewer and/or candidate directions exactly as written.' It also distinguishes itself from AI-generation siblings by stating 'deterministic, no AI generation,' making tool selection unambiguous.

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 gives clear context for when to use this tool: when directions should be set exactly as written and not generated by AI. It also defines preconditions like providing at least one direction field and the stale-source 409 behavior. It does not explicitly name an alternative tool, but the deterministic vs. generative contrast strongly implies when this tool is appropriate.

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