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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, which the description does not contradict; it adds genuine context by clarifying that going back or changing an answer prunes lines from the in-progress draft only, and no saved BOM is deleted. It also names the return payload. Missing details on error/retry behavior keep it below 5.

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?

Four tight sentences, front-loaded with the action, then the loop contract, then the state-mutation caveat. No repetition or filler; every clause earns its place.

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 compensates by naming the return values (updated BOM state, next step options, decision chips) and by explaining the termination condition and session continuity. An agent has everything needed to drive the session correctly.

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% and the schema already explains both message (free text or decision_chip) and session_id (from bom_start_session). The description restates the message semantics without adding format, length, or escaping guidance, so baseline 3 applies.

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 ('Submit') plus resource ('user input for the current step of a BOM session'), and the sibling set (bom_start_session, bom_list_use_cases) makes clear this is the continuation/driving loop rather than session creation. Distinguishable without opening a schema.

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?

Gives explicit operating context: call repeatedly with the same session_id until the session reaches the COMPLETE step, and that the message may be free text or a decision_chip from the previous step. Lacks explicit exclusions relative to siblings, but the loop condition is actionable.

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