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

Annotations already declare mutation (readOnlyHint=false), non-idempotence, and open-world external delivery; the description adds the meaningful business rule that submission is blocked until verification. It says nothing about what happens on an incorrect or expired code, error responses, or rate limits on resends, which matter for a non-idempotent send operation.

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 the two modes, then the mode-selection detail, then the gating constraint — no wasted framing. The sentence 'code verifies the contact' mildly restates the opening clause rather than adding new information.

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 a four-parameter mutation tool with no output schema, the description covers modes, the key precondition, and the code format. Gaps remain on failure behavior and on `quote_id` semantics, but an agent can call this correctly in the common path.

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 must carry the load; it partly does, explaining the expected shape of `code` (6 digit) and the behavior triggered by `resend` plus `channel`. It never mentions `quote_id`, and it omits the channel default of sms and what channel applies when verifying a code.

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 and resource ('Checks the 6 digit code', 'sends a fresh one') and clearly covers both modes of the tool. It is distinguishable from siblings like submit_quote by the verification gate, though it doesn't name any sibling explicitly.

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?

Explains how to select each mode ('code verifies the contact', 'resend=true ... sends a fresh code') and gives the precondition that a quote cannot be submitted until verification. Missing an explicit statement of when not to call it or which quote states require it.

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