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

Beyond readOnlyHint/openWorldHint it discloses substantial behavior: results are a signed document, the default response is a compact view that points at the signed full map, detail: "full" can exceed 100 KB, stored maps can come back with `expired`, unknowns are always shown in full, and empty route families are surfaced as reason no_eligible_provider rather than hidden. It also states the rate-limit posture (free within daily allowance, key lifts it).

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 one long undifferentiated paragraph that front-loads a dense field-by-field description of the return payload. The operationally critical facts an agent needs to invoke it correctly — intent vs intent_id, detail levels, map_id, cost — are buried near the end, making the block harder to scan than its content warrants.

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?

There is no output schema, so the description carries the full burden of describing the return shape and does so thoroughly (per-candidate access facts, capacity, settlement window, economics basis, evidence class, risk and onboarding fields, ordering rule, compact-vs-full). Combined with complete schema coverage on 6 optional parameters, an agent has what it needs to call this correctly.

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 the baseline is 3, but the description adds real meaning: `intent` accepts any form compile_intent takes including payer, `map_id` reads back a previously made map instead of making a new one, and `detail` trades compactness against a >100 KB document. Those are selection-relevant semantics the schema text alone only partially conveys.

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 states a precise verb and resource: it returns the signed Options Map for a PaymentIntent, enumerating every rail and provider the graph holds for the pair and size, with named fields (coverage tier, route_family, regulatory_risk, onboarding_status, payout_rules). It implicitly separates itself from recommendation-style siblings by saying results are 'Sorted by coverage tier, rail class and name, never by a rank' and 'A guide, not advice', but it never names a sibling tool (e.g. route_intent, assess_route, compare_payment_providers) to make the boundary explicit.

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 gives a clear triggering condition — an agent should call this to 'filter out ineligible or blocked routes before quoting' — which tells the agent where this sits in the workflow. It also notes entry paths (an intent in any form compile_intent takes, or an intent_id, or map_id for readback) and cost ('Free within the daily allowance; a key lifts it'). It stops short of explicit exclusions or naming an alternative tool for a narrower question.

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