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

Annotations already declare non-read-only, idempotent, non-destructive, and the description adds real behavioral context beyond them: dependency cycles are rejected, and billing refusals return a `tellHuman` payload with explicit instructions not to silently degrade. It does not state whether the link applies immediately or what other error modes exist, but the failure-mode disclosure is unusually useful.

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 and type semantics are front-loaded, and the billing paragraph, while long and somewhat repetitive, covers a genuine failure mode. A sentence could be trimmed in the billing warning without losing meaning.

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 3-required-param mutation with no output schema and zero param coverage, the description covers link types, cycle rejection, and billing refusal, which is solid. It leaves the source/target directionality and any duplicate-link behavior unaddressed, which an agent needs before calling correctly.

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% for all three required params. The description restates the enum values already present in the schema but never explains the direction of the relation — whether `sourceId` blocks `targetId` or vice versa — which is the single most error-prone semantic for this call, nor what kinds of IDs are accepted.

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 ("Link two issues") and enumerates the four link types, so the resource and action are unambiguous. It does not name a sibling to distinguish from, notably remove_relation, so it stops short of full sibling differentiation.

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?

Inclusion of `blocks`/`blocked_by` as the dependency graph that drives blocking and the cycle-rejection rule gives implied guidance on when to pick those types. There is no explicit guidance on when to use this vs `remove_relation`, or what permissions/preconditions are needed to link two issues.

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