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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context with "Omitted fields are preserved," clarifying that this is a partial/patch update rather than a full replace. It leaves the destructive replace semantics of `where` and `tags` to the schema rather than reinforcing them here.

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 short sentences, zero filler, with the core action first and the blocking prerequisite immediately after. Every clause conveys information an agent needs before invoking the tool.

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 six-parameter mutation with a nested `where` object and no output schema, the description covers the essentials: the action, the mandatory skill prerequisite, and patch semantics. The gap is the absence of any return/confirmation behavior and no reinforcement of the destructive replacement of `where`/`tags`.

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 83%, so the schema already carries most parameter meaning, including that `tags` and `where` fully replace existing values. The description's "Omitted fields are preserved" adds useful optional-parameter semantics but does not address the two required IDs or the shape of `where` beyond pointing at the skill. Baseline 3 is appropriate given the strong 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?

The description states a specific verb and resource ("Updates a RudderStack Data Graph audience"), which cleanly separates it from create_audience, get_audience, and preview_audience in the sibling list. It stops short of naming those siblings explicitly, so the differentiation comes from the verb rather than from a direct contrast.

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?

"MUST call `load_audience_skill` first" is a hard, explicit prerequisite that an agent could otherwise miss, since the `where` schema is an empty object shaped by that skill. It does not, however, state when to choose update_audience over create_audience or preview_audience, so the when-not guidance is absent.

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