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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: drafts are stripped before the user's exclude filter runs regardless of what it says, limit is capped at 50 rather than REST's 100, and format/locale are currently no-ops accepted for forward compatibility. Those no-op parameters are the kind of surprise that would otherwise mislead an agent, but return-shape detail is thin beyond a one-line mention of pagination metadata.

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 behavior and exclusions before the property catalog, which is dense but load-bearing. Some redundancy with the schema's own include/exclude and sort explanations costs it a point, though the catalog itself could not be trimmed without losing queryable-field knowledge.

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?

Covers purpose, exclusions, routing to alternatives, pagination metadata, and the full queryable-property matrix; the output schema handles return structure. Nothing an agent needs in order to build a valid call is missing.

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 goes well beyond it by enumerating every filterable property per collection along with type and sortability — information the schema cannot express and which determines whether an include/sort clause is even legal. It also clarifies AND-vs-OR semantics at the description level for quick scanning.

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 and resource ('Query a collection for paginated content') and immediately scopes what it is not: not free-text search (search_collection) and not single-object fetch (get_object). An agent can distinguish it from all 19 siblings 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 names three alternative tools with the condition that selects each: search_collection for text search, get_object for full records, describe_collection for the complete property list. Also states the routing rule for non-filterable properties, which is the key failure mode an agent would hit.

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