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

Annotations already establish that this is a non-read-only, non-idempotent, non-destructive write. The description adds two useful facts — optimistic concurrency ('with the expected revision') and a cap on the spending limit — but the revision-mismatch behavior is unexplained and the limit note largely duplicates the budget_cents schema text.

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, front-loaded sentences with the action stated first and no filler. The trailing facts are compact fragments, which is efficient though slightly telegraphic.

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, optimistic concurrency, and 50% schema coverage, the description is thin. It never says where to obtain the 'expected revision' (the read sibling), how a mismatch is handled, or what enabling does beyond the schema hints. No output schema exists, so the description carries the burden and falls short.

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 coverage is 50%, so the description must compensate, and it only partially does: it clarifies 'revision' as the expected concurrency token and constrains the spending limit. It says nothing about idempotency_key, environment, installation, or the enabled/lead_capture_enabled settings fields.

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 specific verb ('Update') and the resources it touches ('assistant instructions and escalation permission'). The scope is concrete, but it never names the natural alternative (summer_messenger_assistant_read) or any sibling, so it stops short of full sibling differentiation.

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' implicitly routes the agent away from this tool for factual content, and 'Cannot raise the spending limit' flags a boundary. But there is no explicit when-to-use vs the read sibling or instructions on prerequisites (e.g., fetching the current revision first).

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