share

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

With no annotations, the description carries the full burden and does: it pre-empts the dangerous misreading that content gets sent, states that opening the sheet sends nothing, and documents the file access constraint. That is exactly the behavioral context an agent needs before a share action.

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 short sentences, front-loaded with the action and the payload types, then the safety caveat, then the file constraint. No filler.

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?

Complete for a chooser-opening tool with no output schema: the agent knows what it does, what it accepts, and where files must live. It could mention whether text and path may be combined or that the tool returns once the sheet opens, but nothing essential 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?

Schema coverage is 100%, so all three parameters are already documented. The description adds only a precondition on path (must be in the work folder or chat files) and implies text can serve as a caption, but does not explain the title parameter beyond the schema.

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?

Names a specific verb+resource (open Android's share sheet) with both accepted payloads (text or file) and clarifies the outcome (user picks the app). It is clearly distinguishable from siblings like notify or open_url, which push content without a chooser.

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?

States the use case (let the user pick a target app such as chat, email, cloud drive) and gives a file-location precondition (/root/.buddy/work or this chat's files). No explicit exclusions versus siblings like notify or clipboard_write, but the intent is unambiguous.

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