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

Annotations establish the mutation/safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds genuinely new behavior: what leaves the active list, that content and revision history are retained, that it is a precondition for deletion, and a workflow-stage restriction on changes. That is substantive context beyond the structured fields.

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?

Three short sentences, front-loaded with the core action and effect, followed by the retention guarantee and the workflow-stage caveat. No filler and no repetition of the title.

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 still tells the agent what the tool does, what state changes result, what is preserved, and when the operation is permitted. Nothing needed to invoke it correctly appears to be missing.

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?

There is a single parameter with 100% schema description coverage ('Id of the Instruction.'), so the schema fully documents it. The description adds nothing about the identifier's format or source, which yields the baseline of 3 for a well-covered single-param 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+resource ('Archive an instruction document') and immediately clarifies the exact effect: it leaves the active list and instruction resources while keeping content and revision history. This also implicitly distinguishes it from delete_instruction, which requires prior archiving.

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?

Provides a real usage constraint — during an active workflow run, instruction changes are accepted only in the self-improvement stage — plus a routing hint that only archived instructions can be deleted. It does not explicitly name update_instruction or delete_instruction as alternatives, so guidance is strong but not fully exhaustive.

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