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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact — 'Returns newest first' — but says nothing about result shape, paging behaviour, or handling of zero matches, which matters for an all-optional-filter search.

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?

Two tight sentences with no filler, and the identifying scope ('bookmarks the user already saved') is front-loaded ahead of the filter enumeration and return ordering.

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 five-parameter, zero-required, read-only search with no output schema, the definition covers what can be searched and the result ordering but leaves filter-combination semantics and match behaviour unaddressed — the one thing an agent could actually get wrong when invoking it.

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?

With schema coverage at only 20% (just `limit`), the description has to carry the load, and it partially does: it names the fields `query` scans (title, URL, note, tags, fonts, tech) and maps `color`, `tags`, and `collection` to their concepts. It still never explains how multiple supplied filters interact, nor the expected array format for `tags`.

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 ('Find bookmarks the user already saved') and enumerates the search axes: text fields, colour family, tags, collection. The phrase 'already saved' implicitly separates it from the write-side sibling save_websites, though no sibling is named explicitly.

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?

Usage is only implied by the filter list — an agent can infer 'use this to retrieve saved bookmarks' but gets no guidance on when to prefer it over list_collections, list_tags, or get_design_brief, and no statement about whether filters combine (AND vs OR) or which to reach for first.

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