tool_sharing

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

Annotations already flag destructiveHint=true, readOnlyHint=false, and idempotentHint=false; the description adds real value on top by explaining propagation semantics (copy is detached afterward, shared edits hit every consumer) and warning to confirm before delete_shared. It does not explain the confirmOverwrite flag or what any action returns.

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?

The conceptual distinction that determines correct use is front-loaded, then a dense but scannable action list. The repeated 'Needs:' phrasing is compact and consistent, though the run-on pipe formatting makes the block harder to parse than it needs to be.

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?

For a 14-parameter, nine-action mutation tool with no output schema, the description supplies what the agent most needs: what each action does, what it requires, and which ones are irreversible or propagate to other agents. Remaining omissions (mode, confirmOverwrite) are minor against the complexity covered.

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% across 14 parameters, but the description compensates substantially by listing the required parameter set for each of the nine actions — conditional requirements the flat schema cannot express. Gaps remain: 'mode', 'confirmOverwrite', and the agentIds/orgIds sub-cases of set_access are only covered (or not at all) in 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?

States a specific verb and resource up front ('Copy a tool to other agents or share one tool across the workspace') and immediately disambiguates the two modes: a COPY is independent, a SHARED tool is a single instance used by many. The nine enumerated actions make the tool's full scope legible without opening the schema.

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 copy-vs-share framing plus per-action descriptions give clear guidance on which action to pick, and the consequence clause ('editing it changes all of them') tells the agent when a shared action is dangerous. It stops short of naming alternatives or exclusions, e.g. when to prefer update_shared over update_agent_tool, or that a tool definition must first come from get_agent_tool.

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