get_customer_metrics

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

Annotations are absent, so the description carries the full burden. The description only states the two modes and parameter combinations. It doesn't disclose anything about the return format, whether the tool is read-only, performance implications, or any side effects. For a query tool that presumably reads data, this is a minimal disclosure. Given zero annotations, a score of 2 is warranted because the description doesn't clarify error behavior or output structure beyond the mode.

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 concise and front-loaded: 'Count customers in a country or find the top country.' That is followed by parameter instructions. Two sentences, no fluff. It loses a point because it could be more structured, e.g., listing parameters explicitly, but it is efficient.

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?

Given that the schema provides no property definitions and there is no output schema, the description must explain both input and output. It explains modes but does not describe the return format or any caveats (e.g., does top_country return just the country name or also a count? Does count_by_country return a single number?). For an agent to call this correctly, it needs to know what output to expect, which is missing. The tool complexity is low, but with such sparse schema, the description is incomplete.

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 input schema is empty (no properties defined) and has additionalProperties true, but the description mentions parameters 'mode' and 'country'. Schema coverage is 100% because the schema is essentially empty, so the description provides the only meaning for parameters. It says 'mode=count_by_country with country' and 'mode=top_country without country', which clarifies the parameters. However, it doesn't specify the data types, allowed values for mode beyond two examples, or required status. Since the description does add essential meaning that the schema lacks, but it is not exhaustive, a 3 is appropriate.

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 explicitly states two modes: 'count customers in a country' and 'find the top country'. This is specific enough to distinguish from siblings like get_product_sales or get_revenue_by_period. However, it doesn't name any sibling tool, so it gets a 4 rather than a 5.

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 gives clear context for when to use each mode: 'mode=count_by_country with country' or 'mode=top_country without country'. It implies that if you want counts by country you use count mode, and if you want the top country you use top_country mode. No explicit exclusions or alternatives are named, but the conditions for each mode are clear. This is good but not fully explicit about when not to use this tool.

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