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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuine behavioral context beyond that: the result is 'structured, source-grounded' including direction/materiality/evidence, and it explicitly disclaims trading recommendations or market prediction — useful for an agent deciding whether the output is suitable for its downstream task. 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?

Five sentences, each carrying distinct information: core purpose, required parameter, optional parameter with default behavior, return format, and scope disclaimer. It is front-loaded with the primary function and has no filler or tautological repetition of the tool name.

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?

The output schema exists, so return values are already specified — the description still summarizes them usefully. An agent has everything needed to call it correctly: the required centralBank parameter with examples, the optional date with format and default semantics, and the non-predictive scope. The only minor gap is no explicit guidance on which sibling to prefer for related-but-different needs.

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%, so the schema already documents both parameters, giving a baseline of 3. The description adds real value by clarifying the default behavior of currentStatementDate ('If the date is omitted, the latest available statement is compared') and giving concrete bank identifier examples. That edge is enough to push above baseline.

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 names a specific verb+resource: 'Compare a central bank monetary-policy statement with its immediately preceding comparable statement and return the material changes' across four concrete dimensions (policy language, economic assessment, risk balance, forward guidance). This is precise and distinguishes it from its siblings, which deal with events, market reactions, historical analogs, and upcoming risks — none of which do statement-to-statement comparison.

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 explains how to invoke the tool in its two modes ('latest available statement' vs. a historical date via currentStatementDate) and gives bank-name examples. However, it never explicitly names a sibling as the alternative or states when NOT to use this tool — the closest is the closing disclaimer that it doesn't provide trading advice. The parameter-level usage guidance is strong, but explicit routing away from siblings is absent.

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