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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds real consequence detail the annotations cannot: copies are independent, edits to shared tools propagate to every consuming agent, and delete_shared removes the tool for everyone. That is genuine blast-radius disclosure. It does not cover permission/auth requirements or what happens to existing access grants on failure.

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?

Front-loaded with the semantic distinction between copy and share, then a dense but scannable pipe-delimited action table. Given nine actions it earns almost every token, though the single unbroken block is harder to parse than a short structured list and the final sentences are compressed at the cost of readability.

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, destructive, action-dispatch tool with no output schema, action selection is well covered but the definition says nothing about return values (e.g., new tool IDs after copy, per-agent success/failure for copy_to_agents) and omits two parameters. An agent can pick the right action but not fully predict the response or how partial failures are reported.

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?

With 14 parameters at 50% schema coverage, the per-action 'Needs: ...' lists do heavy lifting, mapping each action to the exact parameters it requires (toolId, targetAgentId, targetAgentIds, scope, access, tool). It also clarifies that copy_to_agents carries variables, and 'chosen agents or client orgs' implicitly maps to agentIds/orgIds. The mode and confirmOverwrite parameters are never mentioned.

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?

The opening sentence names a specific verb and resource ('Copy a tool to other agents or share one tool across the workspace') and immediately distinguishes the two modes of operation, copy vs shared. The nine enumerated actions make the scope unambiguous. It stops short of distinguishing this tool from adjacent siblings like update_agent_tool, delete_agent_tool, or clone_agent, so an agent must still infer boundaries.

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-shared distinction ('A COPY is independent afterwards; a SHARED tool stays one tool used by many agents, so editing it changes all of them') is exactly the decision rule an agent needs before choosing an action, and 'delete_shared — delete a shared tool for everyone (confirm first)' flags the caution case. What is missing is explicit routing to alternatives outside this tool (e.g., use update_agent_tool instead of update_shared for a single non-shared tool).

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