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

Annotations already cover the read-only/idempotent safety profile, and the description adds genuine behavioral context beyond them: results are one row per run, and upstream semicolon-separated multi-file fields are exploded into arrays so a caller does not silently miss the second mate of a paired-end run. Return granularity is disclosed; rate limits or pagination behaviour are not, hence not a 5.

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 dense sentences with zero filler: purpose and return shape first, then the authoritative-use cue, then the paired-end gotcha. Front-loaded and every clause carries information an agent needs.

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?

With no output schema, the description must carry the return contract, and it does — per-run rows containing URLs, sizes and checksums. Combined with the fully-covered input schema this is nearly complete; only edge behaviour (empty results, very large runs, missing files) is unaddressed.

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 100%, so all four parameters (limit, fields, result, accession) are already documented, which sets the baseline at 3. The description restates the accepted accession families and hints at default file-oriented columns but adds no syntax or constraint detail beyond the schema, so it earns no lift.

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 (list every sequencing data file behind an ENA accession) and names exactly what is returned (FASTQ/BAM/CRAM URLs, byte sizes, MD5 checksums). The 'AUTHORITATIVE for where do I actually download the reads' framing cleanly separates it from metadata-search siblings like ena_search and ena_results_types.

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 clear context for invocation: hand it a study, run, sample, experiment or taxon accession and it returns per-run file rows. It signals authority over the download-location question, which implies when to prefer it, but it never explicitly names the alternative sibling (ena_search / ena_results_types) or states when NOT to use it.

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