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

Annotations already declare non-idempotency and non-destructiveness, and the description reinforces the important consequence: 'Uploading again creates another source,' which tells the agent duplicates are created rather than overwritten. It also discloses format and size limits that are not in the annotations. It stops short of describing the returned source object or permission requirements.

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 zero filler, front-loading the action and constraints before the retry caveat. Every clause carries operational 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 return values, and the annotations cover the safety profile. What remains — accepted formats, size cap, encoding, and non-idempotent retry behavior — is exactly what an agent needs to invoke the tool 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 coverage is only 50% (file_name and session_id have no descriptions), but the description compensates usefully: the file-type list constrains what file_name may be, the 10 MB limit bounds data payload size, and 'organization Hub session' clarifies that session_id is a Hub session rather than an arbitrary ID. Base64 encoding is repeated from the schema, which is the only redundancy.

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 ('Attach external evidence') and resource ('organization Hub session'), plus accepted file types and a 10 MB ceiling. It is clearly distinguishable from generic upload or template tools, though it never names the sibling that removes or clears sources, so the differentiation is implicit.

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 one concrete usage rule — 'list sources after an uncertain response before retrying' — which covers the retry scenario well. However, it never says when to prefer this over upload_research_template, or what prerequisite (an existing Hub session) must hold, leaving the core when-to-use decision implied.

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