mosaic_find_similar_targets

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

Annotations already declare readOnlyHint and idempotentHint. Description adds that it returns metadata and metrics, ranks by TM-score, and returns empty results with a populate-hint on fresh DBs, providing behavioral details beyond annotations.

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 two focused paragraphs with no unnecessary words. It front-loads the core function and output, then provides use cases and degradation behavior efficiently.

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 complexity of structural similarity search and the existence of an output schema, the description covers return values (metadata, metrics), edge cases (fresh DB empty results), and intended uses, making it complete for selection and invocation.

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?

Despite 0% schema description coverage, the description explains 'k' (default 10) and implies 'gene' is the input. It adds meaning beyond the schema's property descriptions, but does not fully detail parameter formats (e.g., regular expression for gene).

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 clearly states it finds 'structurally similar targets to a given gene' using Foldseek TM-score. It distinguishes itself from sibling tools like mosaic_search_targets (text search) by focusing on structural similarity.

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?

Provides explicit use cases (paralog discovery, scaffold hopping, cross-family repurposing) and mentions graceful degradation on fresh DBs. Does not explicitly exclude non-structural searches, but context implies when to use.

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