Link code change

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

Discloses the write operation and merge behavior ('Provided fields merge into existing links') and clarifies a non-destructive update with idempotentHint true. This goes beyond annotations by revealing the upsert semantics and its place in the audit flow. No contradiction.

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?

Three concise sentences cover purpose, args, and invocation timing. No fluff. The second paragraph lists args efficiently and the third gives a crisp trigger condition.

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 small, well-annotated tool with a complete schema and output schema, the description supplies the essential workflow placement and merge semantics. Nothing needed beyond what's given; the output schema exists, so return-value detail isn't required.

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 already covers all parameters with examples and 100% coverage. The description adds the merge behavior, telling the agent that partial field updates are allowed and that fields combine with existing links. That contextualizes usage beyond schema descriptions.

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?

The description opens with 'Attach the fix to a feedback item so the loop is auditable' – a specific verb-target-purpose. It names the exact fields (repo, branch, commit, pr_url, diff_summary) and differentiates from sibling tools like loopback_update_status by defining the unique link-record operation.

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?

Explicitly states when to call: 'right after committing the fix, before updating status to fixed'. Provides clear workflow context, implying this tool precedes status updates. No explicit alternatives, but the timing instruction is strong guidance.

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