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

Annotations contain only a title, so the description carries the full disclosure burden. 'Returns metadata' implies a safe read, but it never mentions that as_html flips the response into an HTML table rather than JSON, nor any auth or rate-limit behavior — a material output-shape surprise left undisclosed.

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?

A single front-loaded sentence with zero filler: the return value comes first and the optional filtering qualifier second. Nothing could be trimmed without losing meaning.

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 and a rich input schema, the description is adequate for a simple read tool but omits the HTML response mode that changes the return type entirely, and gives no signal about the sibling tools it replaces in a conversion workflow.

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 100%, so all three parameters are already documented, including the enum values and the comma-separated array form. The description restates the code/type filtering but adds nothing on syntax or defaults, 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?

States a specific verb and resource ('Returns metadata for all supported currencies') and adds scope ('all supported'). The resource is distinct from the rate-oriented siblings (getLatest, getConvert, getRate), so an agent can separate it without opening the schema, 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?

The phrase 'optionally filtered by code or type' implies when to pass filters, but there is no explicit guidance on when to call this versus the rate tools, no prerequisites, and no note that omitting filters returns the full catalogue (that detail lives only in the schema).

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