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

Annotations already declare destructive/non-idempotent/open-world, and the description reinforces this with 'real email... cannot be undone,' adds who it is sent as (user's name/address), a prompt-injection warning, and timeout/error retry behavior. This is rich behavioral context well beyond the structured fields.

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-loads what the tool does and the irreversible nature, then layers the safety procedure and the follow-up step. It is longer than average but every sentence carries actionable information; no filler.

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 destructive, open-world write tool the description covers the safety profile, prerequisites, error handling, and next step, and an output schema exists so return values need not be restated. Complete for the agent's needs.

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 coverage is 100%, so the baseline is 3, but the description adds sourcing context the schema lacks: message_id comes from aiapplyd_get_inbox and the reply targets the newest employer email, and body is the user-approved plain-text reply. Minor added value over the schema's own descriptions.

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 ('Send the user's reply to an email from an employer') and immediately distinguishes itself from the read/draft siblings by naming aiapplyd_get_inbox as the tool not to use for those tasks. An agent can tell exactly what this does and what it does not.

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 explicit when-to-use ('only send on the user's explicit go-ahead'), a concrete procedure (show exact text, then send), when-not (don't use to read or draft), and an error-recovery path via aiapplyd_get_inbox. Nothing is left to inference.

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