update_agent_prompt

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

Given no annotations, the description discloses key behaviors: full replacement of prompt, draft stacking for versioned agents, and the need to publish drafts. It does not mention permissions or failure states, but the draft mechanism is clearly explained, which compensates for the lack of annotations.

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?

The description is four sentences, front-loading the main action. Each sentence adds necessary context without redundancy. Could be slightly tighter, but effectively communicates all essential information.

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 tool with 4 parameters and no output schema, the description covers the draft workflow, the single_prompt constraint, and the replacement semantics. It lacks mention of error handling or edge cases, but provides enough context for an agent to use it correctly.

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 100%, so baseline is 3. The description adds value by explaining that the prompt is a full replacement ('pass the full new prompt text') and that draft_id 'stacks this change onto the draft's other edits', which goes beyond the schema's description.

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 uses specific verb 'update' and resource 'agent's system prompt / instructions'. It clearly states that the full new prompt text must be passed, and that it works for single_prompt agents. It also mentions optional update of first message, distinguishing from sibling tools like update_agent_config which handle other settings.

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?

The description provides context: only works for single_prompt agents, and explains the draft workflow for versioned agents (stacking drafts and publishing). However, it does not explicitly compare with alternatives like update_agent_config or get_agent_prompt, leaving some ambiguity about when to use this tool versus others.

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