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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this with 'Nothing is sent anywhere' and explains why the run is trustworthy (pinned BLAST+ 2.17.0, cross-checked against the real rpsblast program on every bundled protein). It does not discuss runtime, memory, or result size, so it is strong but not exhaustive.

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-loads the core action ('rpsblast, run on this machine: find conserved domains...') before the caveats and the sibling routing. The sentence about version and bundled-protein validation is somewhat promotional, but it is short and each clause carries information.

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 annotations, a full schema, and an output schema, the description only needs to cover scope and routing, which it does: algorithm identity, database size, local execution, and the remote alternative. Minor omissions such as expected runtime for a 1,011-model search are not needed to call the tool correctly.

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 six parameters (including the nested _subject) are already documented with defaults and enums. The description adds only indirect context, the database size (1,011 PSSMs) and that the source can be bundled or NCBI, without clarifying parameter syntax or interactions beyond 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 the exact algorithm (rpsblast) and the exact resource (NCBI SMART domain models, 1,011 PSSMs from CDD), plus the operation ('find conserved domains in a protein'). It also distinguishes itself from the siblings rps_blast_cdd and rpstblastn_smart by naming the CDD-wide alternative, so an agent can place it without opening any 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?

Explicitly gives the selection rule: use this for the SMART subset, and 'for all of CDD use rps_blast_cdd, which goes to NCBI.' The local-vs-remote condition is stated as the deciding factor, which is exactly what an agent needs when choosing among the three domain-search siblings.

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