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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered; the description instead adds non-obvious data semantics: an empty list signals no connected networks, each row is a distinct account, one brand can hold multiple accounts of the same network (e.g. two TikTok), 'todas las redes' silently means all supports_carousel=true accounts, and max_images caps images per network (X allows 4). This is exactly the kind of context annotations cannot express.

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 purpose is front-loaded and every sentence contains operational content, but the description is dense and blends listing semantics with downstream carousel-selection policy (supports_carousel, supports_mixed_carousel, naming chosen accounts in the reply). Some of that guidance arguably belongs to create_and_publish_carousel, making this definition longer and less focused than it needs to be.

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 one-parameter read tool with an output schema (so return values need no explanation) and read-only annotations, the description covers everything an agent needs: empty-state behavior, duplicate networks per brand, carousel filtering rules, alias mapping (Insta, Face, twitter), and ambiguity handling. Nothing essential to calling or interpreting this tool is missing.

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?

There is a single parameter (brand_id) with 100% schema description coverage that already explains sourcing it from list_brands and asking the user when several brands exist. The prose adds no further detail about the parameter itself, so the baseline 3 applies; its extra content concerns selection flags and result rows rather than the input.

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?

"Lista las redes conectadas de una marca" states a specific verb (list) and resource (connected accounts) scoped to a brand, which separates it from siblings like list_brands or get_account_stats. It also immediately distinguishes the empty-result case by routing to get_connection_setup, so an agent knows exactly what this tool does and does not return.

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?

Explicit when-to-use rules are supplied for several concrete situations: empty result means the person has not connected networks, carousels should only use accounts with supports_carousel=true, video carousels need Instagram accounts with supports_mixed_carousel=true, 'all networks' means all carousel-capable accounts without asking, and 'all except X' removes only that network/account. It also states when NOT to ask the user (only on ambiguous name collisions) and names the alternative (get_connection_setup) for the empty case.

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