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

annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered by structured data. The description adds domain context — that metric names are store-specific and enumerable — which is genuinely useful. It says nothing about result size, pagination via cursor/limit, or ordering, which are the behaviors an agent would still need to discover.

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?

Two compact sentences, the trigger front-loaded and the exclusion last, with no filler. The 'claude: installs, ...' shorthand packs information densely but is slightly cryptic and hardcodes only two of the six enum stores.

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?

For a seven-parameter read-only tool with no output schema, the definition covers the selection decision and metric vocabulary, which is the core need. Gap: it omits pagination and response_format semantics.

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 only 43% (store, limit, cursor and response_format are undocumented in the schema), so the description has to carry weight. It partially compensates by enumerating valid metric names for two stores, which is meaningful since metric is a free-form string. But it leaves the other four stores' metrics, plus cursor, limit and response_format, entirely unexplained.

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?

It conveys a specific operation — ranking apps within a store by a published metric — and names concrete metrics per store, so the agent knows what the tool returns. It also names the sibling it is not (charts_get). The word 'leaderboard' never appears explicitly, so the purpose is inferred from 'which apps lead a store', which is clear but one step short of a direct verb+resource statement.

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?

Explicit positive trigger ('use this when the user asks which apps lead a store by a published number') and an explicit exclusion with a named alternative ('Do not use for chart positions; use charts_get'). That is the full when/when-not/alternative triple, leaving nothing to inference.

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