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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond them: each archive is queried independently and hits are interleaved, so adding sources costs latency rather than accuracy, and the result is accessions rather than full records. It still omits rate limits and per-source failure behavior.

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?

A single front-loaded sentence led by the verb and resource, with the archive list as parenthetical detail. It is dense but every clause carries scope information; the nested parenthetical for ENA sub-sources is the only mildly heavy section.

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 read-only federated search with an output schema and fully documented parameters, the description supplies what is needed to call it correctly: what is searched, at what granularity, and what comes back. The missing piece is routing guidance against the many sibling lookup/blast tools, which is a usage rather than completeness 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 coverage is 100%, so 3 is the baseline. The description earns above baseline by giving the query parameter real semantics — free text may be a gene name, protein, organism, or phrase — which tells an agent the intended input style better than the schema's example list alone. The _subject/_files project-reference parameters are left entirely to the 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 ('Search the sequence archives by free text') and enumerates the exact corpora searched (NCBI Nucleotide/Protein, ENA plain/WGS/TSA/features, UniProtKB, iGEM) plus the return shape ('matching accessions'). That is far clearer than a generic 'search'. It stops short of naming the siblings it competes with (find_accessions, blast_search, fetch_record, query_database), so it earns a 4 rather than a 5.

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?

There is no explicit when-to-use or when-not-to-use statement. Usage is only implied: the tool returns accessions, which signals a discovery step that precedes fetch_record/load_record. The only real selection guidance lives in the schema ('asking more costs time rather than accuracy'), not in the description.

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