assetfare_v2_route_selection

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

Annotations already declare readOnly, non-destructive, open-world, non-idempotent. The description adds real behavioral context beyond that: the explicit 'Never approves, prepares, signs, or submits' safety boundary, the absolute 60-second recommendation ceiling with slower routes being 'reference-only,' and the rule that a recent winning range needs two supporting higher buckets and disappears on conflict. These are meaningful traits the annotations don't convey.

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?

It is front-loaded with the core action, which is good, but the middle is dense and cryptic ('a recent winning range needs two supporting higher buckets and disappears on conflict') and some content duplicates the schema's profile enum descriptions. Several clauses feel like internal implementation notes rather than agent guidance, diluting the useful signal.

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 annotations and a full output schema present, the description need not explain safety or return shape. It does cover timing policy and the no-side-effect boundary, but it omits the one thing an agent most needs for a 10-sibling toolset: an explicit statement of when this route-selection tool should be chosen over assetfare_v2_quote or assetfare_v2_quote_selected_candidate. That omission leaves the core selection decision underspecified.

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 100%, so the schema already documents profile timing, chain/token constraints, min-1/max-60 bounds, and the amount semantics. The description mostly echoes profile timing (fast 30s, balanced/economy 60s) and adds the example corridor rather than new parameter syntax. Baseline 3 is appropriate when the schema does the heavy lifting.

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 gives a specific verb+resource: it quotes routes and returns up to two all-in choices with defined labels (assetfare_verified_unsigned / external_provider_handoff). It also implicitly separates itself from write siblings with 'Never approves, prepares, signs, or submits.' However, it never explicitly distinguishes itself from the closely named sibling quote tools (assetfare_v2_quote, assetfare_v2_quote_selected_candidate), so the differentiation is incomplete.

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?

Usage is implied through the example ('compare Solana USDC to Base USDC at USD 347.25 with balanced') and the selection logic described, but there is no explicit 'use this when X, use sibling Y instead' routing. An agent must infer that this is the multi-candidate selection variant rather than a plain single quote, which is a meaningful gap given several near-identical quote siblings.

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