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

Annotations only supply destructiveHint=false, so the description carries the load and does so: no persistence/publication/sending, the return contract (short answer, at most one key question, suggestedReferences with citation rights), the rule that recommendations stay non-binding until confirmed, and advisor-failure behavior that cannot be escalated to a save. This is behavior an agent cannot infer from the schema.

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?

Content density is high with almost no filler, but it is delivered as one long semicolon-chained block mixing purpose, parameter rules, return contract, and failure handling. Only the no-save constraint is front-loaded; the remaining guidance is hard to scan, which weakens selection speed even though nothing is wasted.

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 tool with a deep nested schema and no output schema, the description covers the highest-risk gaps: it spells out return shape, the non-persistence guarantee, the reference-confirmation gate, and degraded behavior on advisor failure. It stops short of explaining draft lifecycle fields (visibility, status, expectedUpdatedAt conflict handling), which is the remaining gap.

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 description coverage is 0%, so the description must compensate, and it partially does: it explains the intent enum (REFINE vs ADAPT_PURPOSE), what context.entryPoint/peerId/conversationId are for, the preserve rule for purpose/targetUserId, and that references are only populated after confirmation. However, the large nested draft object (status, visibility, sectionTitles, contentFormat, expectedUpdatedAt, purposeReviewConfirmed, history) receives no semantic coverage.

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 first clause states a specific verb+resource (draft/revise a cooperation plan per user facts) and immediately negates the confusable actions (does not save/publish/send), which separates it from save_cooperation_plan and publish-type siblings. An agent can identify the operation and its boundary without consulting 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?

It gives explicit routing rules: use intent=ADAPT_PURPOSE when reorganizing an old draft or switching purpose (default REFINE otherwise), pass context.entryPoint/peerId when an object is selected, and only call the save tool on an explicit save request. It also states that approving a draft is not write authorization, which is a genuine when-not rule.

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