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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral context: it mentions each row carries an observation timestamp, source, and staleness status, and that balance 'resolves the applicable tier APY; nothing is fabricated.' It also discloses that it only makes factual comparisons and never recommends providers, which goes well beyond the basic safety hints.

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?

The description is three sentences, each earning its place: first sentence states the core data and sources, second explains the personalization and transparency, third sets behavioral limits. It is front-loaded with the purpose and contains zero filler or repetition.

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 explains what rows contain (timestamp, source, staleness), how each optional parameter affects results (balance resolves tier APY, credit score returns a note), and what the tool refuses to do. It is complete for a read-only data-lookup tool, covering both data content and edge cases around advice.

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 descriptions already cover all three parameters (state, balance, credit_score) with meaningful explanations, and schema coverage is 100%, so the baseline is 3. The description adds a concise summary that the parameters 'personalize the results transparently' and clarifies that credit_score returns a clarifying note only, reinforcing the schema's detail. This adds a bit of value beyond the schema, justifying a 4.

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 opens with 'Current savings APYs: FDIC national average plus rates RateZip observed on institutions' own published rate pages,' clearly specifying the resource (savings APYs) and the scope (FDIC average + observed rates). It distinguishes itself from sibling tools like get_cd_rates and get_mortgage_rates by focusing solely on savings accounts, making the purpose unambiguous.

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 description explains that optional parameters personalize results and explicitly states 'never recommend a provider or claim that RateZip can open an account,' setting clear boundaries for appropriate use. It also says 'decline financial advice without giving allocation or time-horizon rules,' which indicates when not to provide guidance. However, it does not explicitly compare to sibling tools or state 'use this tool when the user asks about savings rates' versus alternatives, so it's slightly shy of a 5.

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