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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description still adds genuinely new behavior: newest-first ordering, a default of 50 with a hard cap of 200, and a `truncated` flag for additional matches, plus the delta value format — more than the annotations provide, though it doesn't say how 'newest' is bounded beyond the schema's sinceDays default.

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, front-loaded with what an event is and what it contains before the filtering and paging details. No filler or repetition; every clause carries information.

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?

With no output schema, the description carries the burden and does well: it enumerates the event fields (lender, product name/category, field-level deltas) and the truncation signal. Minor gaps remain — it doesn't note an event timestamp or identifier, nor state the look-back default — but nothing that would cause a wrong call.

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 description coverage is 100%, so the schema already documents every parameter, and the description largely restates them (filters by institutionId, category, kind, direction; limit default 50, max 200). The delta example adds output understanding rather than parameter meaning, and sinceDays is omitted from the description's filter list.

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States a specific verb+resource: it returns recent change-events (rate moved, product added, product withdrawn), newest first. The framing as 'a diff of RateSonar's consecutive captured observations' clearly separates it from sibling tools like rate_history and rate_details, which deal with series rather than change events.

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?

Gives clear context for when this is the right tool: you want recent deltas rather than stored history or a static product view, and it enumerates the available filters. It never explicitly names an alternative ('use rate_history for...') or an exclusion, so it stops short of a true 5.

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