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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, yet the description still adds real value: what is returned (titles, short descriptions, canonical URLs), what is never returned (private trips, generated advice), and a trust warning that results are untrusted reference material rather than live opening hours, prices, or availability. Auth/rate-limit behavior is not discussed, so it stops short of 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?

Three tight sentences: purpose first, then return shape, then exclusions/safety caveat. Every sentence earns its place with no filler, though the dense enumeration of content types and caveats in one block slightly reduces scannability.

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 bounded read-only search with full annotation coverage and no output schema, the description adequately covers purpose, return fields, scope limits, and trust caveats. The remaining gap is operational detail already noted under parameters (kind semantics, result count/pagination behavior).

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 only 25% across 4 parameters, so the description carries a compensation burden it only partly meets. It clarifies the query and locale dimensions ('topic and language'), but says nothing about the meaning of the five `kind` enum values or the role, default, and 1-10 ceiling of `limit`.

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?

Specific verb + resource + scope ('Search published Mappu pages by topic and language') with an enumeration of the covered content types (audio guides, walking tours, itineraries, product help). It implicitly separates itself from private-trip siblings via 'published'/'never returns private trips', but it never names an alternative tool outright.

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 implied through scope limits ('published', 'never returns private trips or newly generated advice'), which tells the agent when this search is appropriate. However, there is no explicit guidance on when to prefer a sibling such as mappu_get_audio_guide or mappu_read_public_page over this search, and no exclusions stated in comparative terms.

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