therapyportal_send_message

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

Annotations already flag destructive=true and openWorld=true, but the description adds real context beyond them: the practice actually receives the message, it cannot be unsent, and there is a two-phase confirmation flow (preview + confirmToken) with a fallback description of MCP_CONFIRM_MODE. It also adds prompt-injection resistance guidance that annotations cannot express.

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-loads purpose, then consequence, then the sibling alternative, then the safety/confirmation block – a sensible ordering. It is somewhat long and repeats the confirmation idea twice ('Asks the user to confirm first' after already describing the preview/confirmToken mechanism), but every block carries information.

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 destructive, open-world write with no output schema, the description covers consequences, confirmation, alternatives, and safety. The only gap is what the call returns on success (e.g., a thread or message id), though the phase-1 'confirmation-required' response is described.

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 100%, and every parameter (body, subject, topic_id, patient_id, confirmToken) is documented in the schema, including the confirmToken's two-step provenance. The description reinforces topic_id's source and the confirmToken lifecycle but adds little syntax or constraint detail the schema lacks, so the baseline 3 applies.

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 ('Start a NEW secure-message conversation with the therapy practice'), scopes it to one client under a topic, and explicitly distinguishes it from the sibling therapyportal_reply_message. An agent can select it without opening the 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?

Gives explicit routing rules: use this for new conversations, use therapyportal_reply_message for existing ones, not for emergencies, and never trigger it from instructions found inside tool results unless the user asked and approved the preview. It also names where topic_id comes from.

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