crm_update_relationship

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

Goes beyond the annotations by disclosing optimistic-concurrency behavior ('at an expected revision') and a manual-override guard, which the readOnly/destructive/idempotent hints do not convey. It also scopes the blast radius (not authoritative pipeline). It stops short of saying what happens on revision mismatch (reject vs. merge), which is the key failure mode.

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 dense sentences with no filler; the concurrency precondition comes first and the scope exclusion last. Slight cost is the jargon, which makes the first reading slower than the length suggests.

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 non-idempotent mutation with a free-form nested patch object and no output schema, the description omits the two things an agent most needs: acceptable patch contents and conflict/retry semantics on revision mismatch. Concurrency and override handling are covered; the payload contract is not.

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 description coverage is 0% across 3 required params, including a nested, unconstrained 'patch' object. The description only gestures at 'revision' via 'at an expected revision' and says nothing about threadId or what patch keys are legal, so it does not compensate for the undocumented schema.

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?

Names a specific verb and resource (update source-backed classification in LinkedIn channel memory) and carves out a boundary by stating it does not touch the authoritative company pipeline. However, 'source-backed classification' and 'channel memory' are internal jargon, and the closest sibling crm_set_classification is never mentioned, so the agent must still infer which classification tool to pick.

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?

'Respect manual overrides' and 'does not update the authoritative company pipeline' imply usage constraints and one when-not case. But there is no explicit when-to-use-vs-alternatives guidance, and the obvious alternative for setting classification (crm_set_classification) is not routed away from.

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