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

Despite annotations already declaring read-only/idempotent/non-destructive, the description adds substantial behavioral detail: exact unit conversion pairs, region-matching preference, dated ECB currency conversion, the return shape including basis rows (source_url, as_of, region match) and caveats, and the null-with-reason failure mode. The 'never invents a number' guarantee is exactly the kind of trust signal an agent needs.

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?

Dense but front-loaded: the core operation and conversion policy come first, then return shape, then failure behavior, then an example. Every element serves a purpose, though the single run-on opening sentence could be split for readability.

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?

Covers operation, conversion and rounding policy, region preference, return contents, and failure semantics, plus a concrete example. Even though an output schema exists, the extra narrative about basis rows and caveats makes the agent fully prepared to call and interpret the result.

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 80% schema coverage the baseline is 3, but the description adds genuine meaning beyond the schema: currency is converted at a dated ECB rate, country drives region-match preference, and units are converted exactly across acre/hectare, sq ft/m², mile/km. The worked example also clarifies how the parameters combine.

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?

Opens with a specific verb+resource framing ('Arithmetic on published prices: unit price × quantity'), making clear this computes an estimate rather than retrieving raw rows. It distinguishes itself implicitly from retrieval siblings like get_prices or get_stat by emphasizing arithmetic and basis rows, though it never names those alternatives.

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 usage context is implied (you need a cost estimate for a use case) and the fallback behavior (estimate=null with reason when no benchmark fits) tells the agent what to expect. However, there is no explicit 'use this instead of get_prices when…' routing among the many pricing siblings, leaving the agent to infer when this tool is preferred over raw price lookups.

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