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

Annotations already flag this as a non-read-only, destructive write (destructiveHint=true), so the safety profile is known. The description adds nothing beyond that: it doesn't say whether omitted fields are preserved or cleared, whether the change is reversible, or that mutations take effect immediately.

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?

A single short sentence with no waste and a front-loaded verb. It is concise to the point of being thin for a 14-parameter mutation tool, so it is adequate rather than exemplary.

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 destructive 14-parameter update with no output schema and no annotations beyond the safety hints, the description covers only a fraction of the tool's surface and omits any note about partial-update semantics. An agent would have to open the schema to learn most of what matters.

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 100%, so every one of the 14 parameters is already documented in the schema. The description only gestures at 'system prompt or settings', adding no format or constraint detail beyond what the schema provides, so the baseline of 3 applies.

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 resource (existing agent), which is enough to distinguish it from create_agent, delete_agent and get_agent. However, 'system prompt or settings' undersells the actual scope, since the schema lets you change name, tags, status, model, temperature, custom evaluations and more.

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?

There is no guidance on when to use this versus create_agent or delete_agent, no mention of prerequisites such as ownership or permissions, and no note about who may call it. Usage is only implied by the verb.

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