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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavioral facts: deletion is permanent ('for good') and cascades to subgoals and arrows. That cascade disclosure is exactly the kind of context annotations cannot express. It doesn't say what happens to goals linked via link_goals or whether confirmation is required, keeping it below a 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?

Two short sentences, both front-loaded: the effect and its blast radius first, then the usage guardrail. Nothing is wasted and nothing is buried.

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 single-parameter destructive tool with full annotation coverage and no output schema, the description covers permanence, cascade scope, and the invocation precondition. The only notable omission is the effect on goals connected through link_goals/unlink_goals, which matters given the 'arrows' mention.

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% and the description never mentions goal_id, so it adds no meaning about the single required parameter. The parameter is largely self-evident from the tool name, but a note on where to obtain the UUID (e.g., list_goals) would have compensated for the coverage gap.

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 and resource ('Delete a goal') and immediately qualifies the scope with cascade behavior (its subgoals and arrows). This implicitly separates it from delete_subgoal and delete_task without naming them, so an agent can infer the difference, though explicit sibling differentiation would push it to a 5.

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?

'Only when the user clearly asks to delete it' gives an explicit precondition and a caution against over-eager invocation, which is the most important usage constraint for a destructive tool. It stops short of naming an alternative path (e.g., update_goal to modify instead), so it is clear context rather than full when/when-not/alternative guidance.

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