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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description only needs to add context. It adds one valuable behavioral fact — that the response shape is identical to the vertical-specific get tools — but says nothing about miss/not-found behavior or what the returned record page URL and note fields look like.

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?

Very tight — two clauses plus an inline JSON example, with the generic-lookup purpose front-loaded. The fragmentary colon-and-parenthetical style is efficient, though the example could have been annotated to show which fields are required versus illustrative.

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 4-parameter read tool with full annotations and no output schema, the core call path (vertical + slug, obtained from search_entities) is adequately conveyed. But the country parameter is undocumented and no failure mode is described, so an agent would not know how to use or omit country correctly.

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 only 25% (only lang is documented in the schema), so the description must compensate, and it partially does: it explains the vertical+slug composite key and provides a concrete example object showing the expected format. It leaves slug format unexplained beyond provenance, and the country parameter (enum: andorra) is completely unaddressed in both schema and description, which is the notable gap.

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?

"Generic record lookup: vertical + slug" names a specific verb and resource and states the composite key it uses. It also explicitly positions itself against the vertical-specific siblings ("Same output as the vertical-specific get tool (e.g. get_hotel)"), so an agent can distinguish get_entity from get_hotel/get_restaurant without opening either 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 parenthetical "(from search_entities)" implies the expected workflow of searching first to obtain a slug, which is genuinely useful context. However, it never says when to prefer this generic tool over get_hotel or get_restaurant, nor what happens if the vertical/slug pair doesn't exist; the choice between generic and vertical-specific is left to inference.

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