compare_samples

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

The description goes beyond the annotations (readOnlyHint: true, openWorldHint: true) by explicitly disclosing that the tool returns an 'unsupported' error in this build. This is critical behavioral information that prevents an agent from wasting time attempting a call. It is consistent with the readOnlyHint (a compare operation is read-only) and adds the key fact that the tool is non-functional.

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 exactly two sentences: the first states the purpose, the second the implementation status. Both sentences carry essential information with zero fluff, and the most important caveat is placed right after the purpose. This is an appropriately sized and well-structured description.

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 tool that is not implemented, the description is nearly complete: it tells the agent the tool will fail and why. It does not need to explain return values since an output schema exists and the tool is non-functional. However, it omits any hint of which sibling tools could serve as substitutes, which would make it fully complete. Given the tool's unsupported status, the missing alternative guidance is a minor gap.

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 20% (only max_records has a description), and the tool description does not explain any of the parameters. It does not compensate for the undocumented files, samples, interval, or reference parameters. While nested types like FileRef and Interval have rich descriptions in the schema, the top-level parameters remain semantically opaque, and the description adds no parameter-level value.

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's function: 'Compare genotypes/coverage at an interval across files or samples.' This uses a specific verb ('Compare') and resource ('genotypes/coverage at an interval'), and is easily distinguished from sibling tools like get_coverage or get_variants, which retrieve single-file data rather than perform cross-sample comparisons. The additional note that it is not implemented further sharpens the purpose by setting expectations.

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 gives explicit guidance that the tool is not implemented and will return error code 'unsupported' (E9), which effectively tells agents not to use it. However, it does not name alternative tools for comparison tasks, such as get_coverage or get_variants, leaving the agent to infer alternatives from the sibling list. Still, the 'not implemented' warning is a strong and clear usage directive.

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