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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the mutation profile is known. The description goes further by clarifying the side effect is storage-only (no send), which is the key behavioral fact for this tool, plus the builder limitation. It stops short of stating that repeated calls create duplicate messages (non-idempotent consequence), which would be the final piece.

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 'WRITE:' signal and the store-not-send constraint, then the per-type body requirements, then the limitation, then the endpoint. Every clause carries information the agent needs; nothing is padding.

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 14-parameter mutation tool with no output schema, the description covers the operation's effect, the conditional field requirements, and the sending alternatives. Return-value details are not required since no output schema exists. The only minor gap is no note on duplicate creation on repeat invocation.

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 79%, but the description encodes cross-parameter conditional requirements the schema cannot express: 'Email needs email_type, subject and matching body fields (plain: content_text; html: content_html; plain-html: both; raw_html: content_html or content_html_raw)' and 'SMS needs content_sms'. That is real added meaning beyond per-field descriptions, though a couple of params (from_name, is_responsive, reply_to) rely on the schema alone.

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 ('save a new email or SMS message') and immediately bounds the scope with 'This only stores the message; it is NOT sent'. It distinguishes itself from vision6_send_transactional by name, so an agent can route correctly without opening another 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?

Explicitly covers when to use this tool (draft creation), when not to (sending a campaign), and names both alternatives — the Vision6 app and vision6_send_transactional. The 'drag-and-drop builder is not supported' exclusion is an unusually useful boundary that most definitions omit.

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