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

Annotations provide readOnlyHint=false and destructiveHint=false, which the description supports by indicating a non-destructive write operation. The description adds meaningful behavioral context: the submission undergoes human review by a physician, implying asynchronous handling and potential time delay. This goes beyond what annotations convey.

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 three sentences, each earning its place: main action, return behavior, and additional context about physician review. It is front-loaded and contains no redundant 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?

Given the tool has three parameters well-documented in the schema and no output schema, the description covers the essential workflow, return types, and human involvement. However, it does not specify the conditions for returning feedback versus a checkout URL, nor the expected timeframes, which could be useful.

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% with all three parameters described. The description adds value beyond the schema by specifying the required format ('Markdown following the Appendix letter structure') and implicitly clarifying the role of session_token (continuation context). This assists in correct parameter usage.

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 uses specific verb 'Submit' and resource 'clinical encounter letter to the Appendix physician team'. It clearly distinguishes from siblings 'list_conditions' and 'search_knowledge_base', which are unrelated operations.

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 when to use: to submit a clinical letter for physician review. It implies the tool is for one specific workflow and provides context about outcomes (feedback or checkout URL). While no explicit 'when not to use' is given, sibling tools are sufficiently different to avoid confusion.

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