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

Goes beyond the annotations by scoping what cannot be mutated and by disclosing that proposed changes come back as drafts and that long tasks emit progress before the final answer. Annotations only give readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the 'returns drafts, mutates nothing' framing resolves real ambiguity. It stops short of covering auth needs, cost or latency expectations.

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 purpose, then constraints, then the alternative routing, then async behavior — every sentence carries information. The parenthetical list of propose_*/apply_* names is slightly dense but functional; nothing is padded.

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 two-parameter, open-world agent task tool with an output schema, the description covers purpose, mutation boundary, alternatives and async completion. Session semantics live in the schema, so nothing critical is missing; only operational details like latency or rate expectations are absent.

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 100% and both parameters (message, session_id) are already documented in the schema, including the session continuation rule. The description adds no additional meaning about the parameters, so the baseline 3 applies.

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: hands a task to Toffu, the company's AI marketing agent, for analysis, reports and drafts. It also distinguishes itself from the many propose_*/apply_change siblings by naming them as the route for actual changes.

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?

Explicitly frames the use case (analysis, reports, drafts) and the exclusion (no changes to ad accounts, content channels, messages or Toffu settings), then routes the agent to propose_*/apply_change or propose_write/apply_write when a change is wanted. That is direct when-to-use/when-not/alternative guidance.

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