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

Annotations already flag destructiveHint=true, openWorldHint=true and idempotentHint=false, but the description adds genuinely new behavior: the message goes to the real customer, a DRAFT/REVISION proposal transitions to SENT, and a file link is auto-appended when the offer has a file. It stops short of warning that repeat calls re-send to the customer (non-idempotency) or of stating permission requirements.

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 action and the identity of the target, then dense parameter hints in a single wrapped sentence. The nested parentheses make it slightly run-on, but no clause is 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 six-parameter, no-output-schema mutation tool, it covers the identifiers, the required text payload, the delivery target, and the resulting status change. Minor gaps: what happens if both chat_id and chat_uuid are null, and any confirmation or failure behavior after sending.

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 carries the full burden and does so: it supplies the platform enum values (wp|ig|fb|tw), the origin of chat_id and the chat_uuid alternative, and the expected content of message (product, price, validity). All six parameters are addressed despite none being documented in the schema.

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: sends a proposal offer to the customer in their existing conversation, identified by proposal_id or proposal_uuid. The '[publish]' tag and 'Delivered to the real customer' plus 'becomes SENT' implicitly separate it from list_customer_proposals and set_customer_proposal_status, though no sibling is named 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?

Usage is implied rather than stated: the description tells you where chat_id comes from (list_chats) and that an offer must already exist, but never says when to choose this over send_customer_invoice, send_customer_contract, or send_chat_message. An agent must infer the scenario.

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