update_agent_prompt

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

Despite no annotations, description reveals key behaviors: overwriting the full prompt (implied by 'pass the full new prompt text'), draft behavior for versioned agents, and optional first message. Could mention immediate effect for single_prompt agents or validation details, but sufficient for safety.

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 sentences, no redundancy. Front-loaded with purpose, then constraint, then optional behavior, then draft workflow. Every sentence adds value.

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?

Covers purpose, constraints, and draft workflow. Missing output schema means agent may wonder about return value. Could mention if update is synchronous or returns updated agent. Otherwise complete.

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 covers 100% of parameters with descriptions. Main description adds context about overwriting (not appending) for prompt, but no extra detail beyond schema. Meets baseline for high coverage.

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?

Description clearly states verb 'Update' and resource 'agent's system prompt / instructions'. It specifies scope: 'Only works for single_prompt agents' and mentions optional 'first message' update, distinguishing it from siblings like update_agent_config or publish_draft.

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?

Explicit guidance: 'Only works for single_prompt agents' and for versioned agents 'changes are saved as a draft — use publish_draft to make them live'. Tells when to use and when not, and points to alternative (publish_draft).

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