get_variants

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

Annotations declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds critical behavioral context: it explicitly states the tool is NOT implemented in this build and returns error code 'unsupported' (E4). This is valuable beyond annotations and prevents an agent from expecting real results.

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?

Two sentences, front-loaded with the core function, and the critical 'not implemented' warning is placed second. No wasted words, though the 'not implemented' disclosure could arguably be even more prominent.

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?

The description is complete about the tool's current non-functional status, which is the most critical context. However, with 6 parameters and only 17% schema coverage, an agent would struggle to construct correct arguments for a tool that isn't even implemented. The output schema exists but the description doesn't clarify what the 'unsupported' error means for invocation.

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 description coverage is only 17%, so the description must compensate for undocumented parameters. The description mentions 'variant records and optional genotypes' which maps to include_genotypes, and 'overlapping an interval' maps to interval, but it doesn't explain file, samples, pass_only, or max_records semantics. The schema itself documents only max_records, leaving most parameters unexplained.

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 states a specific verb ('get') and resource ('variant records and optional genotypes overlapping an interval'), and the VCF/BCF format qualifier distinguishes it from other genomic retrieval tools. However, it doesn't explicitly differentiate from siblings like get_reads or get_features beyond the format mention, so it's clear but not fully differentiated.

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 for retrieving variant records in an interval, and the format qualifier (VCF/BCF) gives some context. But it doesn't explicitly state when to use this vs alternatives like get_features or lookup_variant, nor does it mention exclusions or prerequisites beyond the 'not implemented' note.

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