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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety bar is covered; the description goes further by disclosing what the computation returns (shortfall versus existing radiator, water flow per radiator, indicative lengths by panel type, comparison sizing). It does not state handling of missing existing_rated_output_w or the accuracy assumptions behind the delta T 50 exponent, which would have made it a 5.

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?

Front-loaded with the core computation, then outputs, then the comparison flag, then a concrete example — dense but every clause carries information, and the example is the most efficient way to convey the nested request shape.

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 7-parameter nested tool with no output schema, the description fills the biggest gaps by enumerating return values and showing a canonical payload. The unexplained trade block and defaulting behaviour for return/compare return temperatures are minor residual gaps that the schema partially covers.

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 57% schema coverage the description must add meaning, and it does: it explains that existing_rated_output_w is a delta T 50 figure, clarifies the flow/return temperature semantics via the mean-water-to-air formula, and demonstrates the nested rooms array with name/heat_loss_w/existing_rated_output_w in the example call. It leaves the trade object, design_temp_c, and the return_temp_c defaulting rule entirely to the schema.

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?

States a specific verb and resource ('works out the rated (delta T 50) radiator output needed') scoped to per-room heat loss and system flow/return temperatures, and gives the governing formula, so it is unmistakably distinct from the sibling sizing tools (size_heat_source, size_pipe).

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?

Establishes clear context for when to call it, including the heat-pump retrofit use case and the specific role of compare_flow_temp_c ('how much bigger radiators must be at a lower flow temperature'), plus a full example call. It stops short of explicit exclusions or naming which sibling to use when the task is heat-source or pipe sizing.

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