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

Far beyond the annotations, it discloses the key trait that this tool does not execute anything ('execute=caller: you call mcp_url and pay that server'), that Down or stale probes are uncallable, that sponsorship does not affect scores, that missing history yields outcome_samples=0 with reason INSUFFICIENT_HISTORY, and that paid REST access costs $0.005 via x402. Annotations (readOnlyHint=true, openWorldHint=false) are consistent with a caller-supplied-candidate ranking operation.

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 lead sentence carries the core purpose and return shape, and every following sentence adds a discrete operational fact. The telegraphic fragments ('execute=caller: you call mcp_url and pay that server') and the unexplained x402 clause cost some readability, keeping it below a clean 5.

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, the description compensates by naming the return fields (pick, fallbacks, reasons) and the sentinel values (INSUFFICIENT_HISTORY, outcome_samples=0), and it covers cost, probe staleness, and sponsorship neutrality. An agent has everything needed to invoke it and interpret the result.

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 100%, so parameters are already documented, but the description still adds real semantics: policy_id comes from set_objective and omitting it falls back to the default safety policy. It adds nothing further for task or candidates beyond the schema text.

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 first sentence names a specific verb (rank), a bounded resource set (1-8 MCP candidates), and the temporal scope (before paying any of them), plus what comes back (pick, fallbacks, reasons). It is clearly distinguishable from record_outcome and set_objective, and it explicitly hands off to set_objective for policy_id.

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 states the decision point for calling it ('before paying any of them') and the handoff from set_objective for policy_id, which is real routing guidance. It stops short of naming when not to call it or what to do for a single candidate, so it is not a full when/when-not/alternative map.

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