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

Adds real context beyond the annotations: login required, non-persistence scope, that saved/sent refer only to this invocation, that EXISTING is a previously stored original, and which sibling handles modification. The 'preview only / no save' claim sits in mild tension with readOnlyHint=false (the tool does produce a plan artifact), which keeps this from a 5.

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?

A single dense block packed with jargon and repeated caveats about saving, sending and looping. It is front-loaded with the login note but overloaded, and several warnings could be consolidated without losing meaning.

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 complex plan-generation tool with no output schema and no parameter descriptions, the definition covers purpose, parameter roles, and the save/send boundaries. An agent has enough to call it correctly, though the preview-versus-persist boundary could be sharper.

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 0%, so the description carries the full burden, and it assigns a role to every parameter — the peerId/conversationId requirement, needId/productId as the counterpart's entry, focusNeedId as the caller's own main line. It compensates well for the empty schema, though it adds no format/type detail beyond what the schema already declares.

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 description states the tool generates a cooperation plan around a specified target using three reuse modes (EXISTING/ADAPTED/DRAFTED) and clarifies it is preview-only, clearly distinguishing it from save_cooperation_plan, edit_cooperation_plan_with_agent and send_cooperation_request. The core action is real but buried inside dense caveat text.

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?

It gives explicit selection conditions: at least one of peerId/conversationId, needId/productId as the peer's entry versus focusNeedId as the caller's own main line. It also states when NOT to save (only on an explicit request), that sending needs separate authorization, and warns against looping drafting — routing guidance that leaves little to inference.

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