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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered; the description adds genuinely new context by naming the pricing model (uw-v1), stating the arithmetic is integer-only, disclosing that slashes can cause outright decline, and explaining that the returned quote_hash lets any party recompute and verify. It stops short of error behavior or limits, keeping it at 4 rather than 5.

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 core pricing purpose and the rate drivers are front-loaded, and the parenthetical is efficient. 'Pure — never mutates bond state' duplicates the readOnlyHint, and leading with 'Underwrite' before clarifying this is only a quote creates a brief ambiguity about whether the tool commits anything.

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?

An output schema exists, so return values need no explanation, and the model/verification story is strong. But for a 7-parameter tool with zero schema descriptions, leaving coverage_minor, duration_days, and slashed_minor unexplained (including units) is a real completeness gap an agent must guess around.

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 0%, so the description carries the burden and only partly succeeds: it explains the directional effect of attestations, successful deliveries, bonds_completed, and slashes, but says nothing about coverage_minor, duration_days, or slashed_minor, and never explains the 'minor' unit convention. Useful meaning is added for about half the inputs.

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 and resource — it produces a deterministic actuarial premium quote for a surety bond from a counterparty's track record — and distinguishes itself from write-oriented siblings (post_bond, activate_bond, slash_bond) by clarifying it is a quote computation. An agent can tell it is a pricing/underwriting call rather than a state-changing bond operation.

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?

The description implies when the rate moves (attestations, deliveries, completed bonds lower it; slashes raise or decline) but never states when to call this versus verify_audit or bond_status, nor whether it is a prerequisite to post_bond. Usage is inferable rather than stated.

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