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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds value the annotations don't: hard limits on `title` (120 chars) and `params` (20 entries), plus the exact identifiers returned (trends_bookmark_id, trends_bookmark_uuid), which is useful for a create call.

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 compact passage, front-loaded with the [write] markers, then the params, then the return values. Nothing repeats the schema and every clause carries information.

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 3-param write tool with a nested object and no output schema, the description covers purpose, constraints, and the shape of the response. Remaining gap is the enumeration of valid `kind` values and how `params` maps to the filter vocabulary of the underlying trend search, which an agent would have to infer.

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 0% and the schema only supplies types, so the description carries the burden — and it does add real meaning for all three params: `kind` mirrors list_trends_bookmarks, `title` is length-capped, and `params` holds search filters as text values with a 20-entry cap, which clarifies the nested object. It falls short of enumerating valid `kind` values or the allowed filter keys.

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 ("Save a trend search as a bookmark") and prefixes it with a [write] tag, so the mutation is unambiguous. It also cross-references list_trends_bookmarks for the `kind` value, which disambiguates it from the many other create_* and trend-related siblings.

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?

The reference to `kind` as in list_trends_bookmarks implies you should enumerate existing kinds there first, but no explicit when-to-use / when-not-to-use guidance or prerequisites (e.g., what happens on duplicate titles) are given. Usage is implied rather than stated.

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