get_reads

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

Discloses the critical trait that the tool is not implemented and returns 'unsupported' (E4), going far beyond what readOnlyHint/openWorldHint annotations convey. Also explains flag filter semantics and the CRAM reference requirement. No contradiction 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?

Three tight sentences, front-loaded with the core function, then flag behavior, CRAM caveat, and implementation status. Every sentence earns its place with no filler.

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 returns an error code in this build, the description tells an agent what it would do, its input requirements, key options, and that it cannot be used. Since an output schema exists, return-value documentation is unnecessary. Minor gaps remain around auxiliary parameters, but overall it is sufficiently complete.

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?

With schema description coverage at only 13%, the description compensates partially: it clarifies 'file' is indexed BAM/CRAM, 'interval' is the query locus, 'reference' is needed for CRAM, and flag filters follow samtools -f/-F. However, it does not add meaning for max_records, include_sequence, or min_mapping_quality, leaving those under-specified.

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?

States a specific verb+resource: 'Alignments overlapping an interval from indexed BAM/CRAM.' This clearly separates it from sibling tools like get_variants or get_signal. The samtools flag filter mention adds further precision about what the tool returns.

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?

Explicitly warns 'Not implemented in this build: returns error code unsupported (E4)', which is a strong when-not-to-use signal. It also gives a prerequisite for CRAM (matching reference unless self-contained). Does not name alternative tools for the unsupported case, so not a 5.

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