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

Annotations only state not read-only, not idempotent, not destructive. The description adds substantial behavioral detail: draft must retain user-selected purpose and targetUserId, GENERAL avoids using entry-object identity, TARGETED revolves around target, preview-confirm before saving, advisor won't re-ask the target, references require user confirmation before inclusion, and recommendations are not auto-linked, saved, public, or sent. This goes well beyond annotations.

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 description is dense but every sentence contributes a distinct operational rule or constraint. It front-loads the main purpose and then adds behavioral and usage conditions; there is no filler or repetition.

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?

The description covers the central workflow: drafting/modifying, intent changes, context passing, preview-before-save, return shape (brief reply, one key question, suggestedReferences), and reference confirmation. It omits details about history and some draft fields, but given the tool's complexity and the agent-driven nature, it is sufficiently complete for correct invocation.

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 0% schema description coverage, the description compensates by explaining intent (REFINE vs ADAPT_PURPOSE), context fields (entryPoint, peerId, conversationId), and key draft constraints (purpose, targetUserId). It does not explain history or the full set of draft subfields, but those are largely inferable from names and types, and the most critical parameters are covered.

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 clearly states the tool drafts or modifies a cooperation plan based on user facts, and adds scope constraints (preserving purpose and targetUserId, GENERAL vs TARGETED behavior). It does not explicitly name sibling tools like save_cooperation_plan or confirm_cooperation_version, so it falls short of full differentiation but remains unambiguous.

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 description provides concrete when-to-use guidance: pass intent=ADAPT_PURPOSE for old drafts or purpose changes, and include context entryPoint/peerId/conversationId when an object was selected from profile or chat. It does not compare against alternative tools, but the within-tool usage conditions are clear and actionable.

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