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

With no annotations, the description carries the full burden and does disclose the response shape (plain-words explanation with formula, effective percent, extras and source citation). It does not mention that results come from a cached pricing check unless fresh=true, nor the 20-page-read daily cap — both of which live only in the schema and affect trust in the number.

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-loaded with the owner-question trigger, then what to supply, then what comes back — three tight clauses, no filler, every sentence earning its place.

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 4-param, no-annotation, no-output-schema tool, the description covers the input needed and the returned contents well enough to call it safely. The only shortfall is not surfacing the caching/rate-limit context that determines whether the number is trustworthy.

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 75% and the schema already examples method and platform values. The description adds meaningful framing by pairing 'the amount' with the '$1,000' example, clarifying it is the gross charge, but 'amount' remains undocumented in the schema itself and nothing is said about defaulting behavior or the trade-off of the fresh flag.

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 diagnostic verb and resource and anchors it in a concrete owner question ('why did PayPal take $35 from my $1,000?'), then enumerates the return contents (fee, formula, effective percent, extras, source). That framing separates it from the raw-lookup siblings like get_fees, though no sibling is named explicitly.

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 a clear triggering condition — use it when the owner questions a specific charge — which is far more useful than a generic 'get fee info'. It stops short of naming when to prefer get_fees or my_effective_rate instead, so a sibling boundary still has to be inferred.

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