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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: bounded previews with authorship and a Linko URL for citation, a fixed 20-result ranked window exposed via limited and count_is_exact, timezone handling for dates, and lenient acceptance of string integers. It does not explain how offset interacts with the fixed ranked window.

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?

The lead sentence front-loads purpose and the remaining sentences each carry distinct information (return shape, alternative tool, timezone, result window, ID disambiguation, back-compat). Some phrasing is terse to the point of being telegraphic ('Exact item IDs disambiguate names'), but there is little waste.

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?

The description does well on return shape and ranking limits, and an output schema exists so return values need not be fully spelled out. However, for a 16-parameter, zero-coverage search tool, key inputs like user_question, alternative_queries, and exclude_ai_generated are left completely opaque, which is a real gap for correct invocation.

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% across 16 parameters, so the description must carry the semantic load and it only partly does: it covers keyword, tag/topic, resource and date filters, timezone, and ID-vs-name disambiguation. Several parameters remain unexplained — user_question, alternative_queries, exclude_ai_generated, note_type, and order.

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 ('Searches the linked account's notes') and enumerates the filter axes it combines (keyword, tag/topic, resource, creation date). It also explicitly distinguishes itself from get_note, which returns full content, so an agent can route correctly 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?

The description clearly signals when to use this tool versus get_note ('get_note returns full content'), which is the most likely confusion given its sibling set. It gives no guidance on when to prefer linko_search, search, or search_resources, so the exclusions are incomplete.

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