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

Beyond the annotations (which already declare destructive=true, idempotent=true), the description adds real behavioral context: merchant-scoped writes, all-or-nothing rejection semantics ('nothing is written'), per-field null rules, and that null/[] clears faqs. It still doesn't say what a successful response looks like, but the mutation contract is well disclosed.

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 scope and identifier lookup, then the constraint, then the key list. Every sentence (scope, refusal behavior, null rules) conveys a distinct rule with 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 partial-update tool with a nested free-form payload and no output schema, nearly everything needed to call it safely is present. The only gap is the absence of any statement about the return value or about behavior when both lead_id and lead_uuid are omitted/supplied.

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% and 'updates' is an untyped free-form object, so the description carries the full burden — and it does: it enumerates all eight allowed key names, gives the inner shape of lead_faqs ({summary, text}), defines clearing semantics, and lists the keys that reject null.

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?

Starts with a specific verb and resource ('Update ... keys of a lead'), states the lookup keys (lead_id/lead_uuid) and the tenant scope. It is clearly distinguishable from edit_lead and from the parallel update_*_keys siblings for other resources.

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 spells out the boundary condition that matters: only allowlisted keys are accepted and any other key causes the whole call to be rejected. It does not, however, explicitly contrast itself with edit_lead or say when to prefer which tool, so routing relies on the agent inferring from names.

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