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

Far exceeds what the annotations convey: it discloses that unknown phrases are refused with the valid list named (never silently downgraded to 'relates to'), that the operation is idempotent, that it requires edit permission on BOTH endpoints, and how cross-company public links behave and decay to 'unavailable'. Annotations only say it is non-read-only/non-destructive; the description adds the real behavioral contract.

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 example and then layered operational detail, with no filler sentences. The final cross-company sentence is a long run-on that stacks several clauses, which slightly hurts scannability.

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?

There is no output schema, and the description compensates by explaining exactly how the result surfaces (on both issues via get_issue's 'links', or under 'publicLinks' with a 'state'). Between permissions, idempotency, refusal behavior and visibility, an agent has everything needed to call it 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 coverage is already 100%, yet the description adds genuine meaning: 'type' is a spoken phrase whose direction is encoded in the words, the arguments cannot then disagree, and a bare 'Blocks' behaves like Jira's outward convention. It also explains that 'to' can be a 'company/KEY-12' reference, beyond the schema's brief note.

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 reinforces it with a concrete worked example ('link_issues("PM-419", "PM-417", "is blocked by")'). That makes it immediately distinguishable from the sibling unlink_issues and from generic issue-mutation tools.

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 strong 'how to get it right' guidance: use the phrase form, that direction lives in the words, and that a bare type name points outward. It does not explicitly name unlink_issues as the counterpart for removal, so alternative routing is implied rather than stated.

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