Appendix

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering safety. The description adds the source 'through Appendix' but doesn't elaborate on behavioral traits like pagination or data freshness. This is adequate but adds minimal value beyond annotations.

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 extremely concise: one sentence with no extraneous words. Every word earns its place.

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 simple list API with one optional parameter and good annotations, the description is mostly complete. It could mention whether the list is exhaustive or paginated, but given the lack of output schema, this is acceptable.

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 parameter 'category' has a description in the schema, achieving 100% coverage. The description does not add further semantics, so baseline 3 is appropriate.

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 clearly states the tool lists conditions and medications from the Appendix, which is specific and distinguishes it from sibling tools like search_knowledge_base that operate on different knowledge. The verb 'List' and resource are explicit.

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?

No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives like search_knowledge_base or submit_encounter, leaving the agent without contextual guidance.

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

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

Annotations already provide readOnlyHint and openWorldHint, so the description's main addition is specifying the type of content searched. It adds some value but does not disclose further behavioral traits like pagination or result handling, which are not critical but could be helpful.

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 sentence that is direct and front-loaded with the action. It is appropriately sized and efficient, with no wasted words. Slightly more structure could improve readability.

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 simple search tool with two parameters and good annotations, the description covers the essential context: what is searched and why. It does not explain return values, but no output schema exists, so this is acceptable. The description is sufficient for its complexity.

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 both parameters already described in the input schema. The description adds no additional parameter-specific meaning beyond what is in the schema, falling at the baseline of 3.

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 clearly states the tool searches 'Appendix's medical knowledge base' for clinical literature, treatment guidelines, and reference material, with a specific purpose to help describe medical issues. It uses a specific verb and resource, and distinguishes well from sibling tools like list_conditions and submit_encounter.

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 implies use when the user needs to describe their medical issue, providing clear context. However, it does not explicitly state when not to use this tool or mention alternatives like list_conditions for listing conditions.

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

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

Annotations indicate it's not read-only, not destructive, and open world. The description adds valuable context: human review by board-certified physicians, possible prescription, and return of feedback or checkout URL. This goes beyond annotations, though it doesn't detail all side effects (e.g., wait time).

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?

Three sentences, front-loaded with the core action, no filler. Every sentence adds necessary 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?

No output schema, but description mentions return types (feedback/checkout URL). It explains the outcome (human review, guidance, prescription). Lacks error handling details but is adequate for a submission 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?

Schema has 100% coverage, so baseline is 3. Description adds extra guidance on the query parameter ('following the Appendix letter structure'), which provides formatting context beyond the schema's character limit.

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 clearly states the action ('Submit a clinical encounter letter'), the target ('Appendix physician team for review'), and the format ('Markdown format following the Appendix letter structure'). It is distinct from sibling tools which are list/search.

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 implies usage context (submitting for review) but does not explicitly state when not to use or mention alternatives. It provides no exclusions or contrasts with sibling tools.

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