save_intent

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

The description discloses that the tool deduplicates the same prompt within 5 minutes per session, which is useful behavioral context not present in annotations. It also clarifies the relationship to the hook, though it does not detail side effects like return behavior or error cases.

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 two concise sentences that convey purpose, use case, and deduplication behavior without unnecessary detail. It is well-structured and easy to parse.

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 simple insert-style tool with no output schema, the description covers the essential context: what is persisted, the relationship to the hook, when to use it, and deduplication behavior. No critical information is missing for an agent to decide to call it.

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?

The schema already describes all three parameters with full coverage, including the default behavior of session_id. The description adds only minimal additional parameter context, such as dedupe behavior involving prompt and session, so it stays at the baseline for schema-covered parameters.

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 clearly states the tool persists a user prompt into the intents table and explicitly names the same source as the UserPromptSubmit hook. It distinguishes itself from normal interactive usage and from sibling tools like save_decision by focusing on programmatic intent seeding.

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 explicitly says to use this tool when programmatically seeding intents and notes that the hook covers normal interactive usage. This gives clear guidance on when to use the tool versus relying on the existing hook.

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