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

Well beyond the readOnly/idempotent annotations, it discloses the carried-forward fill rule (last record only, never the next), the 14-day cap tied to the gap ledger, that carried-forward is not an observation, and the plan-window clamping behavior with windowClamped:true. It also flags that records begin 2026-06-12, so early dates yield nothing observed.

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-loads what the tool returns and the identifiers before the detailed grid semantics, and every clause carries information. The grid/carry-forward sentence is long and multi-clause, which slightly hurts scanability but is not padding.

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?

There is no output schema, so the description carries the return-value burden and does so: observations with dates, the `grid` array and its per-point status/sourceDate/fill shape, gridError on oversized windows, and windowClamped on raised `from`. An agent has what it needs 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?

Schema coverage is already 100%, so baseline is 3, but the description adds real meaning: grid's carried-forward points with sourceDate and fill reason, and the plan-window behaviour that silently rewrites `from`. It does not add format detail for `to`/`from` 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?

Opens with a specific verb+resource: 'Advertised rate history for one product (institutionId and productId)', and states the payload (recorded rate, comparison rate, fees, plus recording date). It never names a sibling tool, though, so an agent must infer on its own how this differs from rate_changes or rate_details.

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 concrete usage conditions: pass grid:true to also get per-day points, note that the record starts 2026-06-12, and that history is capped by plan window with an older `from` silently raised. It does not state when to prefer this over rate_changes/rate_details, so there is no explicit alternative routing.

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