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

Annotations already mark it as a non-read-only, non-destructive, non-idempotent write, so the description just needs added context and it delivers: the linked-goal ordering constraint is a genuine dependency rule not visible anywhere in the schema. It still doesn't say what happens when the constraint is violated (error vs. silently ignored).

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, operation list first, partial-update rule second, edge-case constraint last. No filler and no repetition of the schema.

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?

Covers the full operation set, the partial-update contract, and the one non-obvious business rule, which is sufficient for a 6-parameter tool with no output schema. Remaining gaps — failure behavior on the ordering rule and confirmation of what is returned — are minor.

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 only 33%, but the description carries the meaning for essentially every parameter: text=rename, done=reached/not, important=star, sphere=set sphere, add_subgoal=add. Only goal_id is left implicit, which is self-evident as the required target.

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?

Names the specific verbs and resource up front: rename, mark reached, star, set sphere, add subgoal, all on a goal. Combined with the 'update_goal' name and the sibling set (add_goal, delete_goal, link_goals), an agent can immediately tell this is the field-level mutator rather than a creator or linker.

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?

'Send only what changes' clearly establishes this as a partial-update tool and tells the agent not to resend full goal state. It also gives a real precondition — marking reached requires preceding linked goals to be reached — but it never states when to prefer this over siblings like add_goal or link_goals.

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