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

Annotations only declare readOnlyHint and openWorldHint, but the description adds substantial context those annotations cannot convey: results are synthetic placeholders, nothing is executed, and every call is logged with time, hashed IP, client, tool, arguments, and purpose. That logging disclosure is exactly the kind of behavioral trait an agent should know before invoking. The only gap is that the return value's shape is never described.

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?

Two compact sentences with the core function front-loaded, followed by the operational disclosures. The parenthetical caveat sits immediately next to the claim it qualifies, and the documentation link is a single trailing clause rather than 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 simple three-parameter read-only tool with no output schema, the description covers safety, data provenance, and logging obligations. The one omission is the format of the returned rate (scalar vs. object, precision), which an agent would need since there is no output schema to consult.

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 100%, with both currency codes and the 'purpose' parameter fully documented in the schema itself, so the baseline is 3. The description adds no additional meaning about parameter formats, case sensitivity, or valid code handling beyond what the schema already states.

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 ('Return a placeholder exchange rate between two currencies') and explicitly disqualifies the result as real market data. It does not need to differentiate from a sibling since none of the other tools (execute_script, fetch_url, query_database, read_file, search_documents) overlaps, so sibling differentiation is moot rather than missing.

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 parenthetical 'not real market data' implicitly tells the agent not to rely on this for real financial calculations, which is useful usage guidance. However, there is no explicit statement of when to prefer this tool or what to do instead, and no prerequisites beyond the required 'purpose' argument enforced by the schema.

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