patch_agent_prompt

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

Annotations already declare it is not read-only, is open-world, and is not idempotent, while the description adds important behavior: it refuses a surgical patch when instructions are empty and will not replace the whole prompt with new_string. It also states sync_mirrors defaults false, though the statement 'Never writes vg_instructions' sits awkwardly beside the schema enum entry for vg_instructions.

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 front-loaded with purpose, alternative, and workflow, and most sentences earn their place. It is slightly dense and repeats the empty-field/old_string constraint in two places, but the repetition reinforces an important failure mode rather than obscuring the core instruction.

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 non-trivial mutation tool, the description covers the key operational context: preferred alternative, source workflow, empty-field refusal, target behavior, and mirror syncing. It does not describe return values or success/failure output, but with no output schema and strong annotations that gap is minor.

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 the schema already documents all six parameters thoroughly. The description still adds useful meaning by explaining target=auto and the old_string omission rule, but most parameter-level detail remains schema-driven.

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 and resource: it performs string replacements in the start-node prompt or proactiveMessage/customCSS. It explicitly distinguishes itself from update_agent and names get_agent as the source for old_string, so an agent can identify its role without opening sibling schemas.

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?

Provides explicit when-to-use guidance: 'USE THIS instead of update_agent when the prompt is large and you only need to change a specific section.' It also gives a workflow (get_agent → copy exact span → new_string) and the condition for omitting old_string, leaving little inference.

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