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

Annotations already cover the read-only, non-destructive safety profile, but the description adds real behavioral context: the result is an authenticated resource link, there is an 8 MiB inline ceiling, and oversized originals degrade gracefully to a streaming byte-range endpoint rather than failing.

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 with no filler, front-loading the return value and then the two size/mode branches. Every sentence carries distinct, actionable information.

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 an output schema present, the description need not explain the return payload, and it still adds the auth and size-limit context an agent needs. It does not clarify how the asset relates to sibling getters or what authentication the link carries, a minor gap for this complexity level.

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 50% (id is documented, include_data is not), but the description compensates by explaining exactly what include_data does and its size limit. The id parameter's UUID semantics are left to the schema, which already covers them.

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 ('Return an authenticated MCP resource link for an item's original file'), which is clear about what comes back. It does not explicitly differentiate itself from near siblings such as get_library_object or get_article, so an agent must infer the distinction from 'original file'.

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?

Gives conditional guidance for include_data (use for inline images/audio, or embedding files up to 8 MiB) and notes that larger originals go through a streaming byte-range endpoint. It never contrasts the tool with the sibling library-object or article getters an agent might otherwise pick, so tool-choice guidance is only implied.

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