st.prompt.set_injection

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

With no annotations, the description carries the behavioral disclosure burden. It does disclose that this is a gated operation requiring confirmation and a prior snapshot, which signals a risky mutation. However, it does not explain side effects, reversibility, permissions, or what actually changes in the runtime state.

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 short, front-loaded with the primary purpose, and contains no filler. Every clause earns its place. However, given the tool's 22-parameter surface, the extreme brevity borders on underspecification rather than tight editing.

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?

This is a high-complexity tool with 22 parameters, nested objects, enums, no output schema, and no annotations. The description only conveys the tool's abstraction level and two preconditions. It does not explain the target values, the updates object structure, parameter relationships, return behavior, or failure modes, so an agent cannot safely invoke 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 description coverage is 0%, so the description must compensate, but it only addresses confirm and the snapshot workflow. The other 20 parameters, including target, updates, role, position, and budget, receive no semantic guidance, leaving the agent with almost no help beyond raw schema names.

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 states a clear action, 'Change prompt injection semantics,' and adds a meaningful scoping cue: 'without knowing raw ST setting paths.' This distinguishes it from low-level config-patching tools like st.config.patch, even though no sibling is explicitly named.

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?

It gives clear context on when to use the high-level tool ('without knowing raw ST setting paths') and states prerequisites ('Requires confirm: true and snapshots first'). It does not enumerate exclusions or explicitly name alternative tools, but the use case and workflow constraints are clear enough for an agent to route the call.

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