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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses the exact output contract: per-pair current ratio, 1y change, historical extremes with dates, percentile, distance from low, and lowest-since date. It also discloses the data granularity ('weekly since first common date'), so the agent knows both the safety profile and the observable behavior.

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 dense but efficient: it leads with the core purpose, fully enumerates the ten pairs, then gives the return fields and periodicity. The pair enumeration is necessary because the pair list is the tool's core content, so the length is justified. It could trim some redundancy around 'mirrors...' but overall every sentence earns 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?

With no output schema, this description carries the full burden of explaining the result payload, and it does so thoroughly: exact pairs, exact metrics, date span, and periodicity. It even clarifies that the tool corresponds directly to a public page for cross-reference. An agent can correctly decide to call the tool and know what will come back.

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 already covers the single parameter and all preset slugs at 100%, but the description adds human-readable meaning to those slugs (e.g., India vs US, EM vs US, gold vs US equities). It also confirms that omitting the parameter returns all presets, which is reinforced by the schema. This is meaningful value on top of an already well-covered schema.

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 a specific resource — 'Ratio Chart presets' — and defines exactly what it returns: relative-performance facts for ten named instrument pairs. It lists the exact output fields (current ratio, 1y change, all-time low/high, percentile, etc.), making the tool's function unmistakable and clearly distinct from sibling listing/ranking tools.

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 clearly establishes that this tool is for preset ratio pairs only, not arbitrary pairs, and tells the user which pairs are covered. It does not explicitly name a sibling tool as the alternative for non-preset pairs, but it points to the website mirror for any-pair charting, which gives solid context about the tool's limited scope.

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