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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds real context beyond them: local execution ('run on this machine'), no data egress ('Nothing is sent anywhere'), a pinned engine version (BLAST+ 2.17.0), and validation against bundled GenBank records. It stops short of describing runtime cost or result-volume behavior for a 500-target search.

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?

Front-loaded with the core purpose and scope, then usage and routing. Mostly dense and useful, though the provenance clause ('checked against the rpstblastn program on every bundled GenBank record') is validation boilerplate that does not help an agent invoke the tool.

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?

An output schema exists, so return values need not be described, and the description covers scope, database, execution locality, and the alternative tool. For a zero-required-parameter, all-defaults search tool it is essentially complete, with only runtime/cost expectations left unstated.

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 the schema already documents every parameter (evalue, source, genetic_code, max_target_seqs, comp_based_stats, _subject, sequence). The description only restates the empty-`sequence` behavior already present in the schema, adding no format or syntax detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 ('find conserved domains in DNA'), the exact method ('searching all six reading frames'), and the database ('NCBI's SMART domain models, 1,011 PSSMs from CDD'). It also distinguishes itself from the sibling rps_blast_cdd, which covers all of CDD on a translated protein, so an agent can route correctly without opening either schema.

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 an explicit usage rule ('Leave `sequence` empty to search the open record') and names an alternative with its selecting condition ('for all of CDD use rps_blast_cdd on a translated protein'). It does not, however, address the closely-named sibling rps_blast_smart (protein vs. six-frame nucleotide input), which is the subtlest routing decision here.

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