Search GenCC Diseases

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds value by specifying that the search is performed via a harmonized title (with natural-language and Porter stemming support), MONDO, or OMIM ID, and that results are ranked. It also details pagination behavior: 'the release-bound truncated.next_cursor (surfaced as _meta.next_commands[0]).' No contradictions with 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, using two sentences to convey purpose, search keys, and output. A third sentence provides pagination guidance. Every sentence adds value, with no fluff. The critical information is front-loaded.

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 complexity (5 parameters, output schema exists), the description covers the main purpose, usage context (resolving free text before another tool), and pagination. The annotations provide safety and openness hints. The output schema likely describes the return structure, so the description is not required to detail it. A minor gap: the description does not mention the default values or the effect of the 'limit' parameter.

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 has 5 parameters, but only 'response_mode' (20%) has a description. The description explains that 'query' accepts a harmonized title (natural-language ok, porter-stemmed), MONDO, or OMIM ID. However, it does not explain 'limit', 'cursor', or 'offset' beyond the pagination hint. The description adds moderate meaning beyond the schema but does not fully compensate for the low schema coverage.

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 specifies the action ('search'), the resource ('GenCC disease catalog'), and the search keys ('harmonized title, MONDO id, or OMIM id'). It also distinguishes the tool's output ('ranked diseases with gene/submitter counts') and implicitly differentiates it from sibling tools like 'get_disease_curations' and 'search_genes'.

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 explicit guidance on when to use this tool: 'Use to resolve free text before get_disease_curations.' It also mentions pagination via a cursor, indicating handling of large result sets. However, it does not explicitly state when not to use it or mention alternatives for situations where the disease ID is already known.

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