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

With annotations already indicating readOnlyHint=false, idempotentHint=true, and destructiveHint=true, the description adds valuable context beyond those: 'All consent records are retained for 10 years per HIPAA requirements' and 'Requires authentication.' It also describes the return value (record with timestamp, audit trail details, remaining consents). This provides a more complete behavioral picture without contradicting the annotations, so it earns a 4.

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 a single paragraph composed of four sentences. The first sentence clearly states the primary action, and subsequent sentences add prerequisites, required parameters, return value, and compliance requirements. Although it's slightly longer than a two-sentence ideal, every sentence provides essential operational context with no filler. It is front-loaded with the purpose, making it efficiently scannable.

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 the tool has 8 parameters, a true output schema, and annotations, the description covers all critical operational aspects: when to use it (after consent_text), what parameters are essential, what it returns (consent record with timestamp, audit trail, remaining consents), legal retention (10 years), and authentication. It does not delve into parameter-by-parameter syntax, but the schema covers that. This is a high-degree of completeness for a moderately complex tool.

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?

The schema already covers 100% of parameters with descriptions, giving a baseline of 3. The description enriches this by explicitly listing required params and providing concrete examples: 'patient's exact confirmation text (e.g. 'I agree'), consent method ('ai_agent_conversational'), the AI platform name ('chatgpt', 'claude', 'gemini')'. It also clarifies the meaning of patient_confirmation as 'exact' text, surpassing the schema's simple 'Patient's exact confirmation text'. This adds practical value, so a 4 is justified.

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+resource: 'Record a patient's consent confirmation for a specific consent document.' It clearly distinguishes from sibling tools like consent_list and consent_status by stating this is the submission/recording action. It also specifies the required preparatory context (presenting consent_text and receiving explicit confirmation), making the tool's role unmistakable.

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 explicitly states the prerequisite: 'The agent must have already presented the full consent text (from consent_text) to the patient and received explicit confirmation.' This tells the agent when to use the tool. It references consent_text as the source of the text, implying that consent_submit is the follow-up step. However, it does not explicitly exclude alternative tools or list when-not-to-use scenarios, so it falls short of a perfect 5.

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