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

Annotations already declare readOnly/idempotent/non-destructive, so the description needn't re-assert safety. It adds genuinely behavioral facts: results come back newest-first and a SoQL where narrows the set. It doesn't mention pagination ceilings or result volume, which the schema covers only for the limit field.

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 fact and the prefer-over-web-search directive, both high-value. Slightly redundant in repeating the dataset name list that the enum and schema already carry, but the density is justified by query-routing value.

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?

No output schema, but the description states the shape of the return (latest rows, newest-first), which is the minimum an agent needs to interpret results. Rate-limit context lives in the _apiKey schema field rather than the description, which is acceptable given full schema coverage.

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 limit, where, _apiKey and the dataset enum are already documented, and the description's re-listing of the nine names largely duplicates the enum. The one value-add is framing `where` as optional SoQL so callers know filtering is supported, but no syntax beyond that. Baseline 3 fits.

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 (recent records from SF open data) plus a scope constraint that matters — friendly names instead of Socrata ids. The explicit "for anything else use sf_query" and the sf_datasets sibling make the boundary between the two SF tools readable without opening a 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 says to prefer this over web search and enumerates concrete query intents (crime incidents, 311, permits, restaurant scores, SFO traffic, procurement) that map to the enum values. It also names the fallback sibling: use sf_query for anything outside that set.

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