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

Annotations already declare readOnly/openWorld/idempotent, but the description adds substantive behavioral context: the reviewed=true default exists to avoid drowning in ~30x more TrEMBL predictions, paging is forward-only via an opaque cursor with no offset support, and facets produce server-side count breakdowns. This is exactly the kind of value that goes beyond the annotation hints while remaining consistent with them.

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?

The description is dense but well-organized: it leads with the core purpose, then covers query modes, filtering defaults, facets, paging, and integration with sibling tools. Every sentence earns its place, and the structured flow from usage to boundaries to follow-up actions makes it easy for an agent to parse.

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?

Given the tool's complexity (8 parameters, two mutually exclusive query modes, server-side facets, cursor pagination, and downstream chaining), the description covers all critical operational behavior while the output schema handles return details. It leaves no major usage question unanswered and explicitly names sibling tools for next steps.

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?

Although the schema has 100% parameter coverage, the description adds complementary semantics: it frames text_search vs query as the 80% case versus the advanced syntax, explains the rationale for the reviewed default, states the exclusivity constraint, and clarifies that organism_id is a convenience filter ANDed onto the query. These are meaning-enriching details not fully derivable from the schema alone.

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?

The description opens with a specific verb+resource: 'Search UniProtKB and return curated protein records.' It clearly distinguishes this tool from siblings by calling it 'the discovery entry point' and explaining that result accessions chain into uniprot_get_entry and uniprot_get_sequence.

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?

It gives explicit when-to-use guidance: use text_search for the 80% plain-language case, use query for full Lucene syntax, and exactly one is required. It also specifies when to include TrEMBL via reviewed=false, explains cursor paging limitations, and points alternatives for follow-up record retrieval.

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