link

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

Annotations already cover the mutation/idempotency/destructiveness profile, and the description adds genuinely new behavior beyond them: self-links are rejected, `related` is canonicalized to the smaller id, and `task_ref` is normalized to lowercase kebab-case. It does not say what happens on a pre-existing identical link or what permissions are needed, so it stops short of full disclosure.

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?

Front-loaded with the verb and trigger condition, then the kind vocabulary, then edge-case rules. Every sentence carries operative information and nothing is repeated from 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?

With an output schema present and annotations covering safety, the description fills the critical gaps: enum values absent from the schema, direction rules, self-link rejection, and canonicalization. Only the error/duplicate-labeled outcome and any id-format expectations are left unstated.

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 schema declares `kind` as a bare string, so the description's enum listing is essential and it fully supplies it. It also defines directionality for `part_of` and `answers` and the grouping/normalization behavior of `task_ref`, but the meaning of `source_id`/`target_id` in the general case is only implied.

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?

A specific verb plus resource ('Connect two ideas') followed by the exact conditions and the full `kind` vocabulary. It is clearly distinguishable from read-only siblings like `get`/`related`, though it never explicitly contrasts itself with `related`, which is the closest neighbor.

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?

The opening sentence gives concrete triggering conditions ('when current work reveals they are structurally related, evolved, duplicated, superseding, part of a whole, or answering a question'), which tells the agent exactly when to reach for this tool. No explicit when-not or named alternative is offered.

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