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

Beyond the annotations it discloses partial-update semantics ("values change only the currencies given"), reset behavior ("null goes back to earnrate's default"), that no saved cards are required, and that it operates on the hosted wallet rather than a local file. It does not address the destructiveHint=true side — that existing valuations for a currency are overwritten and whether confirmation is expected — so it is strong but not complete.

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 behavioral sentences are tight and front-loaded, but roughly two-thirds of the text is a 25-item currency mapping run-on embedded mid-sentence, which would be better expressed as schema enum entries. The list is useful yet bloats the definition and disrupts scanability.

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 an output schema present, return values need no explanation, and the description covers scope of effect, reset semantics, preset interplay, and storage location — enough to call it correctly. The notable remaining gap is overwrite/confirmation behavior implied by destructiveHint=true.

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?

The schema documents both parameters, but it leaves the `values` keys as an opaque open object; the description supplies the only available vocabulary of valid currency ids with human-readable names, which the agent cannot otherwise discover. It also clarifies precedence between `values` and `profile` consistently with the schema, adding real meaning beyond structured fields.

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?

"Saves what the user's points are worth to them, in cents per point, in their saved wallet" gives a specific verb, resource, unit, and destination (hosted earnrate wallet). It also states the downstream effect ("every answer then compares cards at those values") which cleanly separates it from siblings like switch_wallet, list_wallet, or set_memberships.

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?

It gives concrete triggering utterances ("I value Chase points at 1.5¢") and a second trigger (user transfers points to airlines/hotels → profile points-heavy), plus the exemption "unless a valuation profile is asked for." It stops short of naming an alternative tool or any when-not-to-use condition, so it is clear context without explicit exclusions.

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