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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-redundant behavior: the BILLING_INACTIVE / MONTHLY_CAP_REACHED refusal mode, the `tellHuman` field, and the warning that all value-bearing writes keep failing until an owner acts. It omits reversibility and what happens when the link doesn't exist.

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?

Purpose is front-loaded in the first clause, followed by the failure-mode guidance. The billing passage is long but each sentence adds an actionable instruction (relay to human, do not absorb, do not continue read-only). No filler.

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?

Strong on the failure path despite having no output schema, which is the hardest part for a destructive mutation tool. However, an agent is left without guidance on parameter direction/type semantics and on the success or missing-link behavior, which matters for a destructive, idempotent unlink.

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%, so the description must carry the burden — and it does not. Nothing explains sourceId vs targetId, and nothing explains the `type` enum (blocks / blocked_by / related / duplicate), whose directionality is exactly what an agent would get wrong when unlinking. 'Same args as add_relation' is a pointer, not a semantic explanation.

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 — 'Remove a link between two issues' — and anchors it against the sibling add_relation, so it is distinguishable from the create-side tool. Slightly short of 5 because the 'same args as add_relation' framing offloads the resource semantics onto another tool rather than stating the entity being unlinked (source vs target issue).

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?

Gives a clear conditional protocol for the billing-refusal path: pass `tellHuman` to the human and do not silently fall back to read-only work. That is real when-to-use/when-not guidance. It does not explicitly state the mirror-image relationship ('use add_relation to create, this to unlink') or prerequisites, so it stops short of 5.

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