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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, and the description does not contradict them. It adds behavior beyond the annotations: the goal is persisted with its recipe, a goal id is returned, and no extraction is performed. It does not go into side effects or failure modes, but that is acceptable given the annotations.

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 sentences with the core action front-loaded in the first sentence and the differentiating alternative in the second. No redundant wording; every clause serves either to define the tool or disambiguate it from a sibling.

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 one-parameter tool with no output schema, the description gives the action, stored data, return value, and a clear pointer to the alternative for extraction. The annotations handle idempotency and safety, and the schema handles param provenance, so nothing needed to call the tool correctly is 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?

Schema description coverage is 100%; draft_id is fully described as coming from cortex_create_goal or cortex_answer_goal. The tool description itself adds no parameter-level meaning, but with complete schema coverage the baseline of 3 is appropriate.

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 ('Saves a settled goal into the memory's goal library'), specifies what is stored (the recipe) and the return value (goal id). It also distinguishes itself from cortex_choose_enrichment by explicitly saying it 'extracts nothing', making the purpose 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?

It gives an explicit alternative: 'cortex_choose_enrichment with choice=describe_goal and that id in goal_ids is what runs it on a source', and the statement 'Still extracts nothing' tells the agent when not to use this tool. Combined with the draft_id provenance in the schema, an agent can route correctly between saving and enrichment.

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