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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real domain context beyond that: results are newest-first, owner_change carries both old and new owners, and 'retired' specifically means the parcel is no longer listed by the county — nuances an agent could not infer from the schema alone. It stops short of disclosing pagination mechanics or default page size.

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 valuable part — what the feed contains and how the kinds are defined. The trailing 'Filter by county, kind, owner name, date or area' is largely redundant given complete schema coverage and could be dropped without loss.

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?

For a 10-parameter, read-only paged list with no output schema, the description covers purpose, ordering, record shape (old/new owners) and kind semantics — enough for correct invocation. Pagination is handled by the self-describing cursor parameter, so its absence from the prose is not a real gap.

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 every parameter is already documented, including format examples for bbox, near and the date fields. The description only echoes the filter set and adds semantic gloss on the kind values, which is marginal beyond what the schema provides; baseline 3 applies.

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 resource (change records produced by update jobs) with a precise ordering guarantee (newest first) and enumerates the three kinds with short glosses, so the agent knows exactly what domain object it gets. It does not explicitly differentiate itself from siblings like search_ownership_records or property_stats, which keeps it from a 5.

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?

'Filter by county, kind, owner name, date or area' describes which parameters exist rather than when to choose this tool over search_properties or search_ownership_records. There is no statement of when-not to use it, no prerequisite, and no alternative named, leaving routing entirely to inference.

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