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

Annotations only declare the mutation profile (readOnlyHint=false, idempotentHint=false); the description adds the operational facts an agent cannot infer: the code is never returned, resends are limited, codes expire, one email is consumed from a daily allowance, and a new code supersedes the waiting one. That is substantive behavioral disclosure well beyond the annotation set.

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?

Purpose is front-loaded in the first clause, and everything after it (quota, expiry, replacement, chaining) earns its place. The middle clause stack ('makes the code, sends it, limits resends and expires it') is dense and slightly run-on, costing a point.

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 mutating tool with no output schema, the description covers the important unknowns: what it returns ('Returns an id'), what it costs, how long the code lives, and what to call next. Error and rate-limit specifics are left implicit, which keeps it just short of fully complete.

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%, with enums-free but documented ranges and defaults for expires_in and code_length, so the schema carries parameter meaning. The description adds only that the destination is 'an address' and that the code is never surfaced to the caller, which is useful but not parameter-specific. Baseline 3 applies.

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 ('Email a one-time verification code to an address') and immediately scopes it with the use cases it serves. An agent can distinguish it from send_email, check_email, and validate_email without opening any 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?

Names the follow-up sibling and the trigger for it ('Then call verify_check with what the person typed'), which is exactly the routing an agent needs. It also explains replacement behavior for repeat calls. It stops short of an explicit exclusion ('don't use send_email for this'), so it is clear context rather than a full when/when-not rule.

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