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

Annotations already declare non-readonly/non-idempotent/open-world, and the description adds real behavioral context on top: the expected-revision precondition (optimistic concurrency) and the hard constraint that the spending limit cannot be raised via this call. It does not clarify whether the nested settings object is replaced or merged, or how idempotency_key interacts with idempotentHint=false, which keeps it short of a 5.

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, front-loaded with the action and the concurrency precondition, then the two caveats. Nothing is wasted, though the phrasing is telegraphic and could have spent one clause on the settings-object behavior instead of omitting it.

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 with a nested settings object, no output schema, and 5 required parameters, the description covers the revision and budget constraints but omits the two things an agent most needs: whether the update is a full settings replacement or a partial merge, and what a successful response contains. Adequate but with clear gaps.

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 50% schema coverage and 6 parameters including a nested object, the schema already explains budget_cents, daily_budget_cents, and escalation_enabled. The description only adds meaning for `revision` (the expected revision) and reinforces the budget constraint; it says nothing about how `settings` fields not supplied are treated, leaving a meaningful gap.

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 names a specific verb/resource pair ('Update assistant instructions and escalation permission') and adds the concurrency requirement ('with the expected revision'), which is not obvious from the name alone. It implicitly contrasts with summer_messenger_assistant_read, but does not distinguish itself from adjacent update tools like summer_messenger_voice_update or summer_company_settings_update.

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?

'Company facts live in shared knowledge' implies the agent should route factual content elsewhere rather than stuff it into instructions, which is a useful steering hint. However, there is no explicit when-to-use/when-not or named alternative tool, so the guidance is implied rather than stated.

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