Fflsharetext

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

With no annotations, the description carries the full burden, and it does a good job disclosing return values, the QR-in-terminal behavior, and the sandbox networking constraint that no annotation or schema field expresses. It omits important behavioral facts about the underlying session—e.g. that a link is served only until maxDownloads/timeoutSeconds elapse and that sessions persist until fflStopSession—which are material for a tool with 23 parameters.

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?

Purpose and return values are front-loaded, followed by a clearly labeled policy block and a short QR note. The closing IMPORTANT presentation directive is somewhat agent-instruction rather than tool definition, but every block is scannable and earns its space.

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?

An output schema exists, so return values need not be detailed, and the description still names sessionId and link. Given 23 parameters with no annotations, the sandbox policy and terminal-QR note fill the biggest gaps, though the session lifetime and security posture of an exposed download link are not addressed.

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 91%, so the baseline is 3; the description exceeds that by explaining the joint semantics of forceRelay and preferredTunnel in sandboxed environments, which the schema fields alone do not convey. The remaining parameters (e2ee, receipt, recipientAuth, etc.) are left to their schema descriptions.

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 ('Share text content') and names the return values (sessionId and link). The resource type cleanly separates it from siblings such as fflShareFile and fflShareBase64 without needing to inspect their schemas.

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 managed-sandbox policy gives explicit conditional guidance for when to set forceRelay=True and preferredTunnel="default:web", including a negative rule for local CLI environments. However, there is no guidance on when to choose this tool over fflShareFile/fflShareBase64/fflShareFiles, so tool-selection is only implied by the resource name.

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