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

Annotations already declare readOnlyHint and openWorldHint, but the description adds real behavioural context beyond them: every figure is labelled LIVE, INDICATIVE, HISTORICAL or ESTIMATED, and estimated savings are never realised, which tells the agent how to read the output. It also discloses the commercial model ('Free: shares the route-assessment allowance') and that a single analysis endpoint backs every payment-intelligence tool. The POST endpoint behind a readOnly hint is worth noting but is a kept analysis resource, not a contradictory side effect.

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?

Extremely tight: one front-loaded sentence defines the comparison and its outputs, then two short fragments cover the service and the data-quality caveat, then one on cost. No filler, and the most decision-relevant information leads.

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 15-parameter, nested-object tool with no output schema, the description does well to name the returned figures and the reliability labels. However it leaves open how to choose between the mutually exclusive input paths (amount vs beneficiary_amount, invoice_text vs individual fields, currency vs source/destination currency) and gives no visible indication that no parameters are strictly required, which an agent needs before calling.

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 all 15 parameters are already documented in the schema, and this establishes a baseline of 3. The description reinforces the comparison basis ('at the same amount and against the same official rate') but adds no meaning to weights, priority, existing_provider structure or the invoice_text-vs-fields alternative beyond what the schema already says.

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 names a specific comparison: the agent's current provider placed beside every route on record for the corridor, at the same amount and official rate, with named output metrics (all-in bps, total cost, beneficiary amount, eligibility, score). It is clearly a provider-vs-market comparison rather than a cost calculation or a route recommendation. It stops short of naming the nearest siblings (price_routes, recommend_payment_route, swapeazi_route_compare) it must be distinguished from.

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 only implied: the phrase 'Your current provider beside every route' signals the scenario (you already have a provider quote and want to benchmark it), and 'Read a kept analysis instead of making a new one' appears only in the schema. There is no explicit when-not guidance or pointer to alternative tools when the agent has no existing provider or merely wants raw rates.

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