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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the definition tells us this is a non-destructive but non-read-only operation. The description adds nothing about what actually happens: whether the filtered subset is persisted as a new collection, whether the original collection is altered, whether the non-selected records are discarded, or what is returned. For a mutation-flagged tool with no output schema, this is a significant transparency gap.

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?

A single well-formed sentence with the action verb front-loaded and zero filler; nothing is redundant. The terseness is appropriate but borders on under-specification given how much behavior is left undecided.

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?

With four parameters, no output schema, 0% schema description coverage and mutation semantics flagged by annotations, the description is too thin for the tool's complexity. An agent cannot confidently predict whether the operation mutates the collection or what it returns, which is essential information for a filtering tool with a write profile.

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 0%, so the description carries real burden here. It does add meaning by mapping the three filter axes to the three optional parameters (IDs, source collection IDs, location), which is more than the bare schema names provide. However it gives no format for bbox coordinates or ordering, no upper-bound/maxItems guidance, and no statement of how multiple supplied filters interact or what happens when all are omitted.

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 names a specific verb ('keeps' i.e. filters) and resource ('selected records of a collection') and enumerates three filter axes: by ID, by source, by location. An agent can map these to record_ids, source_collection_ids and bbox. It stops short of differentiating itself from plausible siblings (filter_by_area, combine_collections, get_collection) or stating whether the result is returned or written back.

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?

There is no when-to-use guidance at all: nothing says when to filter a collection versus calling get_collection or filter_by_area, whether the filters combine with AND semantics, or whether this can be chained with operations like combine_collections. The agent is left to infer the tool's role purely from the name.

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