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

Annotations already declare readOnlyHint and openWorldHint, but the description adds material context the agent cannot get from them: the tool is paid and requires an Authorization Bearer key with a pricing URL, and it produces 'a signed decision record' that should be retained and later passed to the reconcile tool. It also discloses the external benchmarks used (bank advertised rates, official business-payment average, G20 lines), which explains the open-world behaviour. It does not cover latency, rate limits or failure modes.

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 opening fragment 'Before money moves:' front-loads the timing well, but the body collapses into a long run-on clause chain ('your quote measured if you pass one, beside what banks advertise, the official business-payment average and the G20 lines') that is grammatically incomplete and forces re-reading. Most content earns its place, but the packaging costs comprehension.

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 an 11-parameter tool with a nested object and no output schema, the description covers purpose, cost/auth, the nature of the return artifact and the follow-up tool, which is a reasonable floor. It does not describe what the signed decision record actually contains (scored routes, ruled-out entries, pass/fail shape), so an agent cannot anticipate the response structure.

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 every parameter, including the verbose allowed_providers explanation and the nested quote object. The description echoes three of them conceptually ('maximum LDI, maximum settlement time, regulated provider required') and mentions measuring a held quote, but adds no syntax, defaults or edge-case guidance beyond what the schema supplies. Baseline 3 is appropriate.

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 concrete action on a concrete resource: every eligible route for a payment is 'scored against your own limits', with the limit dimensions named (max LDI, max settlement time, regulated provider). It also implicitly separates itself from recommendation tools by insisting it is 'evidence against your policy, never a recommendation'. What it lacks is any explicit naming of close siblings such as assess_route, check_constraints or swapeazi_route_compare, so an agent must infer the boundary.

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?

'Before money moves' anchors the timing clearly to the pre-execution stage, and the handoff instruction 'pass it to swapeazi_guardrail_reconcile once it settles' defines the lifecycle relationship with a specific sibling. There is no statement of when NOT to use it versus the other assessment tools in the family, which keeps it out of 5 territory.

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