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

Adds substantial behavior beyond the annotations: it discloses that the current referrer is replaced (the destructive effect the destructiveHint only hints at), that concurrency is guarded via expectedUpdatedAt with a stale_revision return, and that retrying with the same idempotencyKey replays the first result. It also flags the auth requirement ('you may view/update') and warns that field values are untrusted content.

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-loads the core purpose, then layers prerequisites, concurrency, and idempotency details, with the security note separated cleanly. Sentences are dense but each carries distinct information; 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 mutation tool with no output schema, it covers purpose, the mutation effect, permissions, concurrency, and idempotency well. It does not state what a successful call returns beyond the stale_revision error case, a minor gap given no output schema exists.

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?

With only 17% schema description coverage, the description compensates by explaining the three non-obvious parameters: referrerContactId (person id, or null to clear), expectedUpdatedAt (obtained from get_record), and idempotencyKey (retry semantics). objectType and id are self-evident and workspaceId is documented in the schema, so coverage is effectively good.

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 precise verb+resource ('Sets or clears the referrer') and even defines the domain term parenthetically ('the person who referred the business'), scoped to 'one lead or deal you may update'. It is unambiguous what the tool does, though it never explicitly distinguishes itself from the broader update_record sibling.

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?

Usage is implied through prerequisites ('Needs expectedUpdatedAt from get_record') and permission scoping ('one lead or deal you may update'), which tells the agent the workflow. There is no explicit when-to-use-vs-alternatives guidance, so the agent must infer that this is preferred over a generic record update.

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