Get Recent Changes

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavioral detail: results are paginated and anchored to a checkpoint, deleted records surface as deleted:true with only a LOD URI and datestamp, and identifiersOnly output omits objectNumber. It does not discuss rate limits or what a resumption token invalidates beyond filter-ignoring, which the schema covers.

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 purpose, then layered detail on mode selection, follow-up calls, and deletion handling; nearly every clause carries operational information. It is on the dense side for four sentences but avoids filler.

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 six-parameter paginated feed with an output schema present, the description supplies everything an agent needs that the structured fields don't: checkpoint anchoring, the identifiersOnly trade-off, and how deleted records appear in results. Return-value details are rightly left to the output schema.

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 the baseline is 3, but the description adds meaning beyond the schema by explaining the functional consequence of identifiersOnly (headers only, no objectNumber, requires re-run to act) and the shape of deleted records. The remaining parameters (from/until/setSpec/maxResults/resumptionToken) are only echoed from 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 a specific verb+resource+scope: an OAI-PMH delta feed of records changed within a date range, anchored to a harvest checkpoint. This is clearly distinguishable from sibling search/browse tools because it is change-oriented rather than query-oriented, and it names the downstream tools (get_artwork_details, get_artwork_image) it feeds.

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 concrete routing guidance: use identifiersOnly=true for a lightweight listing and re-run without it when you need to act on a change, plus it names the follow-up tools keyed on objectNumber. It lacks an explicit 'when not to use this' (e.g., versus search_artwork for enumerating a corpus), so it falls just short of the top band.

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