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

The description discloses cost (1-2 AI credits), side effect (overwrites old narration), return value (new narration), and failure preconditions (incomplete run, narration_enabled=false). This is exactly the kind of behavioral context that annotations do not provide, especially since all hints are false/uninformative. No contradiction with annotations.

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?

Three dense sentences, each adding critical information: purpose and scope, cost and side effect, and refusal conditions. No filler, front-loaded with the primary action. Efficient and well-structured.

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 mutation tool with two required parameters, the description covers purpose, preconditions, cost, side effects, and return value. An output schema exists, so return format is handled elsewhere. No missing context that would prevent an agent from using 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 coverage is 50% (run_id has description, forecast_id does not). The description adds context by tying both IDs to an 'existing completed forecast run' and highlighting that run_id must reference a completed run. However, it does not explicitly define forecast_id's role (e.g., the owning forecast), leaving some ambiguity. Partially compensates for the coverage gap but not fully.

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 opens with a specific verb and resource: 'Re-run ONLY the AI narration step against an existing completed forecast run.' This clearly distinguishes it from running the full forecast (e.g., run_forecast) and other siblings. The scope is precise and immediately understandable.

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 states when to use the tool (regenerate narration on an existing completed run) and explicitly identifies refusal conditions (run not complete, narration_enabled=false). It does not name an alternative tool, but the 'ONLY' phrasing and mention of 'no engine work' imply when not to use it (for full re-runs). Clear context with minor room for explicit sibling differentiation.

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