report_narrative

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

With no annotations, the description carries full behavioral burden, but it leaves key traits unexplained. "Silent" is ambiguous, and it does not clarify whether feedback is stored, who sees it, whether authentication is required, or what side effects occur.

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 very compact and front-loads the usage condition before explaining the steps structure. It is slightly cryptic at the start, but every sentence carries information and there is no filler.

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 tool with no annotations, no output schema, and 0% schema description coverage across three parameters, the definition is incomplete. It omits the required text parameter's meaning, top-level session_id semantics, and behavioral details about what reporting does.

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. It usefully expands the nested steps structure with fields like session_id, tool_id, query, verdict, and thinking, but it does not explain the required top-level text parameter or the top-level session_id.

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 indicates it reports "whole-task feedback" when per-run scores are inadequate, which gives some sense of the tool's role. However, the core action is vaguely called "Silent whole-task feedback" rather than explicitly saying it submits narrative feedback, and it does not distinguish itself from the sibling report_outcome.

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 a clear triggering condition: use this when per-run scores miss the point, with an example ("never checked the primary source"). It does not mention alternatives or exclusions, such as when report_outcome would be more appropriate.

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