unlink_records

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

No annotations are present, so the description carries the burden. It discloses that the tool returns REVIEW_REQUIRED, that it is a direct legacy write, and that it preserves full relationship details in source history. It does not cover auth or failure modes, but for a one-parameter tool the key behavioral caveats are present.

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 short sentences front-load the most important warning (legacy, REVIEW_REQUIRED, alternative) before the instruction. 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?

For a simple one-parameter tool with an output schema, the description covers purpose, legacy status, the primary caveat, the alternative, and parameter semantics. It doesn't describe exact return structure, but the output schema is already provided; minor missing details are auth or prerequisite conditions, which are not necessary for an agent to decide against using this tool or to call it with relationship_id.

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 0%, so the description must compensate. It does by specifying that relationship_id is the link's own ID (not record IDs), and that removing it preserves relationship history. This adds meaningful semantics beyond the bare parameter name, though it doesn't describe format or type beyond the schema's string.

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 identifies a specific action ('Remove a wrong link by its own ID') and resource (link/relationship records), and explicitly distinguishes the tool from the modern write flow by labeling it 'Legacy direct write' and naming prepare_write/commit_write. This is more than a restatement of the tool name.

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?

It explicitly instructs agents to use prepare_write/commit_write instead, and frames this tool as a legacy fallback for removing a wrong link. That gives a clear when-not condition and names the alternative, satisfying the highest bar.

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