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

With no annotations provided, the description carries the full behavioral disclosure burden. It does well by explaining the upsert semantics ('One note per session'), automatic sensitivity resolution, and the important side-effect caveat that no DeliveryProof or practice points are created. It omits details like auth requirements, rate limits, or return format, but the disclosed behavioral traits are valuable and non-obvious.

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?

The description is compact and front-loaded with the primary purpose. The subsequent sentences earn their place by covering upsert behavior, sensitivity handling, and a critical caveat about delivery confirmation. It is slightly dense in the middle but remains readable and free of fluff.

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?

Given eight input parameters, no output schema, and no annotations, the description covers the core context: what the tool does, upsert semantics, sensitivity behavior, and a key integration caveat. It does not describe the return value or all parameter semantics, but the most decision-relevant context is present, making the tool usable with reasonable confidence.

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 0% and the description must compensate. It does add meaning by listing clinical fields (evolution, treatmentPerformed, nextSessionPlan) and expanding the 'type' enum values. However, it does not explain required parameters like orgSlug and sessionId, and it mentions 'progressMetrics,' which is not present in the input schema, creating potential confusion. The compensation is partial, not complete.

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?

The description opens with a specific verb phrase 'Create or update the clinical note (ficha) of a session' and enumerates key fields, making the resource and action unmistakable. It also distinguishes itself from sibling tools like session_note_get and delivery_confirmations_list by clarifying that this is the upsert operation and explicitly excluding delivery proof creation.

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?

The description states exactly when to use the tool ('Create or update the clinical note of a session') and provides an explicit when-not: it does not create provider-confirmed DeliveryProof or award practice points. It also directs users to the provider portal/REST for delivery confirmation, which is a clear alternative. This is textbook usage guidance.

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