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

Annotations cover the safety profile (destructive=true, idempotent=true, openWorld=true), and the description adds substantial context beyond them: re-checks of delegation, permission, evidence, route, policy and funding; the distinction between submission status, provider receipt and removal status; the reconciliation-required path; credit reservation and returned operation_id; and matching auth scope. This is exactly the extra behavioral detail the annotations cannot convey.

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?

Front-loaded with purpose and dependency, then compactly enumerates rechecks, result semantics, retry rule, auth and credit behavior. Every sentence carries information, though the density makes it slightly hard to scan.

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 a destructive, credit-consuming mutation, the description compensates by explaining what is returned (operation_id), how to retrieve results (poll get_operation), and how to interpret partial success (provider acceptance does not prove removal, reconciliation required). Nothing essential to correct invocation is missing.

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 both quote_id and idempotency_key are already well documented in the schema. The description adds only the reminder that task input lives inside the quote, which the schema also states. 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?

States a specific verb+resource ('Submit a prepared packet through a supported, activated enforcement route') and distinguishes itself from siblings prepare_takedown and create_quote by making the quote prerequisite explicit. An agent can tell what this does and what it depends on without opening the 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?

Gives the required sequencing ('First create_quote(action="submit", ...)'), the retry rule ('reconcile the original operation before any retry'), and the sandbox caveat. It never explicitly says when NOT to use it versus prepare_takedown, but the workflow context is clear enough to route correctly.

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