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

The description discloses a key behavioral trait beyond the annotations: the 15-minute default delay when scheduled_at is not provided. This is valuable because the annotations only say readOnlyHint=false and destructiveHint=false, which don't convey the scheduling behavior. The description doesn't mention whether this creates a draft or sends immediately, but the scheduling detail is a meaningful behavioral disclosure.

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?

The description is a single sentence that front-loads the core purpose ('Schedule an email to a candidate') and immediately follows with the most important behavioral nuance (the 15-minute default). Every word earns its place; there is no fluff or repetition of schema details.

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 tool with 11 parameters and no output schema, the description is relatively complete but leaves gaps. It doesn't explain what the response looks like (e.g., the created message ID), whether the email is sent immediately or queued, or how to handle threading (send_in_new_thread). The 15-minute default is helpful, but an agent might need to know if the tool returns a scheduled message object or just a success status. Given the parameter count and no output schema, a bit more context would be warranted.

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 64%, so the schema documents most parameters. The description adds the crucial default for scheduled_at ('now + 15 min'), which is not fully explicit in the schema ('default: now + 15 min' is in the schema, but the description reinforces it). However, the description doesn't explain the semantics of parameters like application_id, reply_to_email_id, or send_in_new_thread beyond what the schema already provides. With 64% coverage, the description partially compensates but doesn't fully bridge the gap for undocumented parameters like cc, bcc, and application_id.

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 verb and resource: 'Schedule an email to a candidate'. This clearly distinguishes it from message-related siblings like hires_batch_create_messages, hires_update_message, and hires_patch_message. It could be slightly clearer about whether it creates a new message vs. sends an existing one, but the verb 'schedule' and the schema fields (to, subject, body) make the core purpose clear.

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?

The description gives a clear context for when to use this tool: when you want to schedule an email to a candidate. It also explains the default behavior when scheduled_at is omitted. However, it doesn't explicitly state when NOT to use it or name alternatives like hires_batch_create_messages for bulk sending or hires_update_message for editing an existing message. The context is clear enough for an agent to select it for single-candidate email scheduling.

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