linear_issue_relation_create

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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description must add the real behavior — and it does disclose the non-obvious directional semantics that annotations cannot express. It stops short of covering failure modes an agent would care about: whether duplicate links error, whether the relation is reversible/removable, or whether it needs write access to both issues.

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 sentences, zero redundancy, and the core action plus relation vocabulary is front-loaded before the directional caveat. Nothing needs trimming or reordering.

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 simple mutation with no output schema, the description covers the action, the valid relation vocabulary, and the one genuinely ambiguous aspect (directionality). It is short of full completeness only in omitting permissions/error behavior, which for an open-world write call would be worth a line.

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 100%, so the baseline is 3, but the description earns extra: the schema's own field descriptions for issueId ('the issue that is related') and relatedIssueId ('the related issue') are nearly indistinguishable, and the description resolves the ambiguity by defining which side does the blocking/duplicating. It does not address the optional 'id' field or the 'input' wrapper, hence not a 5.

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 ('Link') and resource ('two issues') and enumerates the four supported relation types. An agent can immediately distinguish this from siblings such as linear_issue_create or linear_search_issues, which do not touch relations.

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 directional note tells the agent how to order the two issues for 'blocks' and 'duplicate', which is useful invocation guidance. However, it never states when to reach for this tool versus alternatives (e.g. comments or labels for soft associations), nor any prerequisites such as required permissions on both issues.

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