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

Annotations only declare destructiveHint=true, but the description discloses far more: it spends credit, costs per SMS part by encoding, can partly fail ('failures lists the refused numbers, which are not charged'), is never retried, and returns message ids/status. This is rich behavioral context beyond the annotation.

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 operator-relevant signals ('WRITE, SPENDS CREDIT') and every clause carries information (cost, failure mode, retry policy, limits). It is a dense wall of text with parentheticals, slightly heavy for a single sentence, but no waste.

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?

No output schema, yet the description explains the accept reply (message id and status, price maybe later), partial-failure semantics, and cost, and routes to smsmode_get_balance and smsmode_list_messages. An agent has everything needed to invoke and recover correctly.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning beyond the schema - why encoding matters for cost ('GSM7: 160 characters for 1 part...'), that send_at schedules rather than sends now, and that stop is legally required for French marketing. It reinforces rather than merely repeats 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 one SMS text to 1-10 recipients) plus the scope constraint (batch of unit messages, no campaigns or lists). An agent can immediately distinguish this from reading siblings like smsmode_list_messages or smsmode_get_message.

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?

Explicit prerequisites ('Check smsmode_get_balance first'), exclusions ('no campaigns or lists'), and a named alternative with its trigger ('after a timeout or error, check smsmode_list_messages (ref_client) before sending again'). 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.