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

Annotations already declare the mutation/non-destructive/non-idempotent profile, and the description goes beyond them by disclosing validation behavior ('loops are refused') and the ordering rule that determines a valid link. It stops short of saying what happens on a duplicate link or how to undo one.

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 tight sentences: the mechanism first, then constraints and examples. No filler, and the critical ordering rule is not 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 two-required-UUID mutation with no output schema, the description covers purpose, direction, cross-period validity, and loop rejection — enough to call it correctly. Missing only edge behavior (existing link, archived goals, undo path).

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 0% and the two UUID parameters carry no descriptions, so the description must carry the semantics — and it does: 'from one goal to another: reach the first, then the second opens' combined with 'earlier period first' implies from_goal_id is the prerequisite and to_goal_id the dependent. It never names the parameters explicitly, so a small inference step remains.

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 uses a concrete verb-image ('draw an arrow from one goal to another') plus a functional gloss ('reach the first, then the second opens') that makes it clear this creates a prerequisite dependency between two goals. It is distinguishable from the delete/update siblings, though it never names the closest alternatives (unlink_goals, build_goal_flow).

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 supplies real usage constraints — direction must follow chronological order, and loops are rejected — plus examples of legal cross-period links (month goal to year goal). However, it gives no explicit 'use this instead of X' guidance against unlink_goals or build_goal_flow, so the agent must infer when this tool is the right one.

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