compare_interface_costs

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds substantial behavior an agent could not infer: source studies and dates, the exact return fields (hidden markup pp, PRO maker/taker base, gap in pp), unverified status of Bitstamp Basic, subscription caveats (Kraken+ waiver, Coinbase One), the fact that app volume earns no PRO tier credit, and residency blocking for Bitvavo/Bitpanda/BISON.

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 opens with a very long, run-on Chinese quote blob of user phrasings and then continues with dense multi-clause sentences packing statistics, caveats and return-field enumerations. Useful content is present and front-loaded, but the size is far beyond what routing requires and the trigger list is excessive relative to its marginal value.

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 and minimal annotations, the description carries the full burden and does so: it documents return fields, evidence provenance, per-venue coverage limits (unverified Bitstamp, no PRO interface for Bitpanda/BISON), residency gating, and the cross-tool side effects. An agent has enough to call and interpret the tool 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 interpretation: country applies per-venue residency gating (with named venue-blocked cases), monthly_volume_usd drives a specific annualized-excess calculation, and language scoping is implied by the outputs described. The exchange parameter's modeled set is also restated with concrete slugs, adding mild value beyond the schema.

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 core sentence states a specific verb and resource: it 'compares each venue's CONSUMER interface ... against its own PRO order-book benchmark on the same account,' and it enumerates exactly which venues and interfaces are modeled (Kraken app, Coinbase Simple, Bitstamp Basic, Bitvavo one-tap, Bitpanda/BISON spread-model). This is directly distinguishable from sibling tools like compare_exchange_fees, whose rows merely receive the hint, so an agent can route correctly without opening a schema.

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 explicit triggering contexts (user questions about app pricing, hidden spread, two price tiers) and conditions like passing country for residency gating and monthly_volume_usd for annualized excess. It does not state when NOT to use it versus the sibling cost tools, only that its output is injected into them, so it falls short of a full when/when-not map.

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