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

Annotations only supply destructiveHint=true; the description adds meaningful context beyond that: the message is REAL, it MODIFIES live data, and it consumes message credits. That cost/irreversibility angle is genuinely useful. It stops short of stating whether sends can be undone or throttled.

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?

Two dense sentences, front-loaded with the highest-stakes fact (real send, modifies data, costs credits). The trailing REST-body enumeration is somewhat redundant with the schema but serves as a quick contract summary; the emphasis caps are justified by the risk.

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 7-parameter mutation tool with no output schema and only a destructiveHint annotation, the description supplies the missing risk framing (live data, credit spend). It omits delivery confirmation behavior and rate limits, which are minor given no output schema is defined.

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 100%, so the baseline is 3. The description restates the body keys (contactPhone, text, accountPhone, mode, subject, fallbackText, mediaItems) but adds no formatting, ordering, or interaction rules beyond what the schema already documents.

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?

Opens with a specific verb+resource in caps ('SENDS A REAL SMS or MMS to a recipient') and pins down the exact REST operation (POST /messages) with its JSON body. This clearly separates it from read-side siblings like get_message, list_messages, and evaluate_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?

Gives an implicit usage rule ('Provide only the optional fields you need') and warns of real-world cost, which frames when to invoke. However, it never names or contrasts an alternative — notably the sibling evaluate_message, which an agent might prefer for validation — so the when/when-not decision is only partially covered.

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