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; the description still adds substantive behavior: drafts are auto-hidden from anonymous callers, and results carry a public url with a total count. It stops short of describing anything about result ordering or the absence of paging beyond `limit`, which keeps this from a 5.

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?

Core semantics are front-loaded in the first four sentences, and the collection catalog is a clearly separable reference appendix. The catalog is useful but largely duplicative of list_collections/describe_collection and adds bulk; the schema's `collection` examples ('blog', 'products') also conflict with the catalog's actual collections.

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 an output schema present, return-value detail is not owed, and the description covers searchability, access-controlled draft hiding, and sibling routing. It leaves minor gaps around result ordering and the fact that only a single capped page (limit ≤ 50, no offset) is available, plus the collection-example mismatch.

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 a 3 is the baseline, but the description adds meaning beyond the schema: it defines which properties are actually searchable per collection (the listed catalog) and that other schema properties are not searchable. That scoping is not derivable from the schema and materially changes how an agent phrases queries.

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 opening sentence gives a specific verb, resource, and scope ('Free-text search within a single collection') and immediately describes the return shape ('items decorated with a public `url`; total reflects what was found'). The description also names the boundaries against siblings: get_object and describe_collection for full records, query_collection for field-value filtering.

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 states explicitly what this tool does not do ('does not filter by field value — use query_collection with `include`/`exclude`') and routes the agent to get_object/describe_collection when the full record or full property list is needed. Search modes (AND default, OR, quoted phrases) are spelled out up front.

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