Get KPIs (full records)

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

Annotations already establish read-only, idempotent, closed-world behavior, so the bar is lower. The description adds genuinely useful context beyond them: that formula and data-source fields exist only for the 44 detailed KPIs (partial data, not an error), that the library is 88 entries, and that unfiltered calls paginate through the entire set.

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?

Very tight — every clause carries information (data availability, lookup mode, filter logic, pagination scope) and the record contents are front-loaded. The heavy backtick-per-parameter style makes it slightly dense to parse, but there is no filler.

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 annotations cover the safety profile. The description covers data completeness caveats, filter combination, and pagination scope, leaving only the mechanics of `limit`/`cursor` continuation slightly implicit. Adequate for a 5-param, no-required-args read tool.

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 60% and the description fills key gaps: it defines slug as exact-match lookup, explains capability as 'featured on or officially related to', and clarifies featured_only's dual meaning with and without capability. It also explains filter interaction (AND) and the resulting empty result set. `limit` and `cursor` remain undocumented in both places, costing a point.

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 (look up / filter / page through) and resource (full KPI records), and enumerates exactly what a record contains: description, formula plus candidate data sources, related capabilities, and featured locations. That level of content specification lets an agent distinguish it from sibling list/detail tools like list_capabilities and get_capability without opening the schema.

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 clearly states the two usage modes — single-record lookup via `slug` versus filtered/paged browsing — and explains the AND combination rule plus the zero-record gotcha when a slug conflicts with a capability filter. It does not, however, point to any sibling tool for adjacent needs (e.g., when to use get_capability instead), so it stops short of explicit alternatives.

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