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

The description adds useful side-effect context beyond the annotations: it sends a security confirmation email, does not change permissions, and prohibits retrieving the code. It does not elaborate on the destructiveHint annotation, but there is no direct contradiction, and the annotations already flag the destructive nature.

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?

Two sentences, front-loaded with purpose and precondition, with no filler. Every sentence adds necessary operational or safety 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?

The description covers purpose, timing, side effects, and a safety constraint, but it omits parameter mapping and the next logical step after the code is sent (e.g., confirming with confirm_dossier_access). Given no output schema and multiple closely related siblings, this leaves some workflow ambiguity.

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 low (33%), with only idempotencyKey explained in the schema. The description does not explain proposalId or revision, and only obliquely refers to them via 'the exact access preview', so it fails to compensate for the coverage gap.

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 specific action—request a one-time code at the authenticated person's verified email—and clearly distinguishes this from the actual confirmation step by saying it does not change permissions. An agent can tell this is the pre-confirmation code-request step, not confirm_dossier_access.

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?

It provides a clear precondition ('After presenting the exact access preview') and a strong behavioral constraint ('Never retrieve the code yourself'). It does not explicitly name alternatives or when not to use this tool, but the context makes the intended step clear.

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