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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows it's safe. The description adds valuable behavioral context: the promotion label is 'SEPARATE, disclosed' and 'never a rank input' – crucial to understand that promotions don't affect ranking. It also describes the eliminated block, showing resource cost of constraints. This goes beyond annotations, though not deeply into rate limits or performance.

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 lengthy but information-dense, covering purpose, parameters, usage, and output. However, the final sentence 'Returns: Qualifying candidates with aligned comparable facts, fact-only organic_rank, separate promotion label slot, and an eliminated block.' duplicates the earlier sentence 'Returns qualifying candidates with aligned facts and a FACT-ONLY organic_rank, plus a SEPARATE, disclosed `promotion` label slot (never a rank input), and an `eliminated` block...' This redundancy could be trimmed, but otherwise it's well-structured.

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 there is no output schema, the description fully covers expected outputs, including the organic_rank, promotion label, and eliminated block. It also explains the input structures thoroughly, covering both candidate scope modes. For a tool with this complexity (4 params, nested objects), the description is complete and self-sufficient.

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%, but the description adds substantial semantic detail: it explains the structure of constraints with concrete examples ({dimension:'geo',op:'includes',value:'NG'}) and clarifies the candidates property's two valid forms. Also explains limit default via 'default 20' in schema, but description doesn't repeat it. The description adds value over schema by explaining the elimination semantics and the discover mode, making parameter usage clear.

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 the tool's purpose: 'Compare federation tenants on their structured choice_profiles to pick one for a need.' It identifies the specific resource (federation tenants) and the action (compare to pick), and distinguishes it from siblings like federation_catalog_search_multi (which searches) and federation_choice_get (which retrieves a single choice profile) by focusing on comparison and selection.

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?

Explicitly states when to use: 'Use this to choose a tenant before buying via the catalog/order path.' Also explains the two candidate scope modes ('after a catalog search' vs '{discover:true,vertical?} to find candidates by need'), giving clear context for selecting the appropriate input format. It indirectly differentiates from search tools by requiring a prior catalog search for tenant_ids, and provides alternatives implicitly through the candidates scope.

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