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

With no annotations provided, the description carries the full burden of disclosing behavior. It states what the tool returns (variants, count, group) and clarifies that it is descriptive, not a health ranking. However, it lacks details on whether the operation is read-only, if authentication is needed, or how the variant criteria (ESM2, AF) are defined. The output schema exists but is not referenced.

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 at two sentences, covering essential information without redundancy. Every phrase adds value: the criteria for variants, the fields returned, and the behavioral caveat. It is well-structured and front-loads the purpose.

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's simplicity (one parameter, output schema present), the description covers the main outputs and a key behavioral note. However, it does not define terms like ESM2 and AF, which may be unclear to an agent without domain knowledge. It also does not guide the agent on how the breed parameter is interpreted (e.g., fuzzy matching). While an output schema exists, the description could be more complete within its own text.

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 input schema has 0% coverage (no description on the breed parameter), and the description does not elaborate on the expected breed value. It mentions 'Breed profile' but does not specify format, examples, or allowed values (e.g., common name vs. scientific name). This leaves ambiguity for the agent, especially since there are no enums.

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 that the tool returns a breed profile including top damaging common variants with specific criteria, number of dogs, and breed group. It implicitly retrieves this data, and the additional note 'Descriptive only — not a health ranking' helps distinguish it from health-related tools like disease_bridge or disease_links. However, it could more explicitly name the action verb and differentiate from siblings like breed_variant_frequency.

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 provides minimal guidance on when to use this tool. The note 'Descriptive only — not a health ranking' hints at a limitation, but it does not explicitly compare with sibling tools such as breed_variant_frequency, breed_similarity, or breeds_in_atlas. There is no advice on when not to use it or what prerequisites exist.

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