hebbrix_report_outcome

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, but the description adds specific behavioral details: how to avoid double-counting via correction, safe reuse of idempotency_key, and rejection of conflicting reuse. It also clarifies that this is a writing operation for outcomes. These details go beyond the raw annotation flags, providing operational context that helps agents handle side effects appropriately.

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 the core purpose in the first sentence, followed by structured parameter-specific guidance. It consists of six sentences, each adding distinct value (value ranges, metrics prerequisite, final/correction semantics, idempotency). It is slightly lengthy but remains efficient and organized, avoiding redundancy.

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?

Given the high parameter count (8) and zero schema coverage, the description is notably complete: it explains most parameters, their interactions, and prerequisites. It does not describe the output (though an output schema exists) or detail confidence, but these gaps are minor. Overall, the description provides enough context for an agent to use the tool 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?

With schema description coverage at 0%, the description takes over parameter explanation entirely. It covers success/reward values, metrics declaration requirement, final and correction flags, and idempotency_key behavior. Though it omits confidence and decision_id, these are self-explanatory from names and the required status of decision_id. The description fully compensates for the missing schema descriptions.

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 it 'Report the REAL delayed result of a prior hebbrix_choose_action', specifying the exact verb ('report') and resource ('prior hebbrix_choose_action'). This distinguishes it from siblings like hebbrix_choose_action (which selects actions) and hebbrix_remember (which stores general memories). It precisely communicates the tool's role in the workflow.

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 gives clear context: use after a hebbrix_choose_action, with explicit options for early vs. final reporting ('Set final=false for an early signal and report the settled value later') and correction ('Set correction=true to replace previously learned evidence'). It also mentions a prerequisite for custom metrics (must be defined via REST API). While it doesn't name alternative tools, it clearly frames this as the outcome-reporting tool, making when-to-use unambiguous.

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