Fed Hike Pass-Through

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false), lowering the bar. The description still adds real behavioral context beyond them: 'one source per bank,' per-row source type, and observation dates, which tell the agent how to interpret provenance and freshness of each row.

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 dense sentences: the first front-loads what is computed and the exact output fields, the second covers dataset structure and the optional filter. No filler, no repetition, and the most important information leads.

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 read-only, single-optional-param tool with an output schema and full annotation coverage, the description supplies what's needed: the computation being reported, row granularity, provenance, and the filter. The only marginal gap is that it doesn't touch freshness/staleness expectations, but get_rate_freshness exists as a sibling for that concern.

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% and the single optional institutionId is fully documented in the schema (including example ids like tab, ally, marcus). The description merely restates that the filter is optional and scopes it to 'one institution id,' adding no format or behavior detail beyond the schema, so the baseline 3 applies.

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 (return Fed-hike pass-through per savings account) and enumerates the exact metrics returned: rate before, rate now, basis-point change, pass-through share, days to move. That framing cleanly separates it from siblings like get_top_hysa_rates or get_bank_gap, which measure levels and gaps rather than pass-through of a specific hike.

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?

Usage is only implied: the description notes the result can be 'optionally filtered to one institution id,' which hints at the unfiltered-aggregate vs single-bank modes. It never states when to reach for this instead of get_bank_gap, get_reality_score, or best_move_this_week, nor any precondition for calling it.

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