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

Annotations already signal readOnlyHint, openWorldHint, and idempotentHint, so the tool is well-characterized as a safe, side-effect-free operation. The description adds specific behavioral context: api_key is optional on public endpoint but required on /mcp/mcp, which clarifies authentication behavior. It does not detail what happens when no more pairs are left or how the strategy affects selection, but annotations lower the burden. No contradiction.

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 compact and front-loads the core purpose. The strategy list is efficient and the api_key note is a separate, clear sentence. No redundant filler. It is appropriately sized for a simple tool with a short parameter list.

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 the presence of an output schema and annotations that indicate a safe read operation, the description covers the essential call premise: what to expect (next pair), how to choose strategy (list), and an authentication caveat. It does not explain the difference between strategies or edge cases (e.g., exhausted pairs), but this is partially mitigated by the output schema and does not block correct invocation. Adequate but with gaps for nuanced usage.

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 description coverage is 0%, so the description must compensate, but it only adds clarity for two parameters: 'strategy' (lists valid values) and 'api_key' (optionality conditions). The 'ranking_id' parameter is not elaborated, but its purpose is fairly self-evident from the tool name. The description adds some value beyond the schema (strategy semantics) but does not fully cover all parameters.

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 clearly states that the tool retrieves 'the next pair of entities to evaluate' for a given ranking. This verb+resource structure is explicit and distinguishes its purpose from siblings like 'get_daily_pair' and 'predict_matchup_winner'. However, it doesn't explicitly state the context of 'matchup' evaluation (e.g., pairwise comparisons) beyond the name, but the description does not conflate it with other actions.

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 lists available strategies with 'adaptive' as default, implying usage contexts for each (e.g., balanced vs random). It does not explicitly provide when-to-use vs when-not-to-use guidance or compare to alternatives. The statement about api_key requirements gives an important usage condition but not strategy selection. This is implied rather than explicit.

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