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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description contributes one piece of behavioral context beyond that—that each size is returned 'with each size's source'—but says nothing about result volume, ordering, or what happens when data is missing for a platform.

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?

One front-loaded sentence with no filler, and the returned-content detail is placed where the reader needs it. It is appropriately sized for a trivial single-parameter read tool, though it could have spent a few more words on the platform parameter rather than the parenthetical list.

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?

With no output schema, the description does carry the burden of describing returns, and it does so adequately by naming the size categories and the accompanying source attribution. However, for a lookup tool whose only parameter is undocumented, the definition leaves the agent guessing about default scoping and overlap with sibling reference tools.

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% and the single parameter 'platform' is never mentioned in the description at all, so the description adds no meaning beyond the enum values themselves. Crucially, it does not explain the consequence of omitting the optional platform parameter, which is the one semantic gap an agent must resolve before calling.

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?

The description uses a specific verb and resource ('Returns recommended image sizes per platform') and enumerates the asset categories covered (posts, Stories, covers, banners, thumbnails, profile pictures), so the agent knows exactly what content comes back. It does not differentiate from siblings like get_platform_specs or get_safe_zones, which cover adjacent platform-reference territory.

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?

There is no when-to-use guidance, no when-not-to-use, and no mention of the sibling reference tools (get_platform_specs, get_safe_zones) that an agent could easily confuse this with. The description never says whether calling it without a platform returns all platforms or errors, which is the main usage decision an agent faces.

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