convert_data

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description supplies the substantive behavior: which files are created, that existing outputs are refused unless overwrite=true, that the user must be consulted first, and how to read the resulting report (summary.n_loci_passed, failure_reasons, output_files). This is well beyond what the annotations convey.

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?

Dense but front-loaded: the first sentence states the action and outputs, then bulleted option groups, then the report-reading guidance. No filler sentences; the length is justified by 15 parameters and no schema documentation.

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 complex multi-parameter tool with no output schema, the description covers inputs, side effects, user-confirmation requirements, return-field interpretation, and the follow-on tool. The only small gap is units/precise meaning of a few numeric thresholds (min_dp, min_bq, het_freq), though their grouping under 'read-based calling' gives adequate context.

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 15 parameters and 0% schema description coverage, the description documents essentially every argument: phasing enum values (iupac | split | haploid | vcf), its applicability limits, phased_vcf pairing, reference, the five locus filters, the four read-calling thresholds, overwrite semantics, out_prefix resolution ('relative to the project'), and files accepting globs. It fully compensates for the empty schema.

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 and resource: convert inspected data into BPP input files (bpp-seqs), and enumerates the exact artifacts written (PREFIX.txt, .imap, .stats.tsv, .loci.tsv). It is clearly distinguishable from the sibling inspect_data it references.

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?

Gives explicit prerequisites ('Use the same files and imap as inspect_data'), conditional guidance tied to input type ('BAM/CRAM and gVCF input only' for phasing; 'does not apply to alignments'), a user-interaction requirement ('Ask the user whether their diploid data are phased'; 'Ask the user first' before overwrite), and a next-step route ('Next: build_species_tree').

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