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

The description adds valuable behavioral context beyond the annotations: it explains that the input is processed by an AI editor that translates the free-form note into concrete adjustments (topic preferences, settings, deep-dive requests). This is a significant disclosure of how the tool works internally. The annotations already indicate non-destructive, non-read-only behavior; the description appropriately amplifies that with no contradictions.

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 two sentences long with no wasted words. The first sentence front-loads the purpose and gives concrete examples, and the second explains the mechanism and places it in context ('the main way a person retunes their news feed by talking'). Every sentence and phrase earns its place.

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 3 well-documented parameters, no output schema, and clear annotations, the description is complete. It explains what kind of input is expected, what happens internally (AI editor translates into concrete adjustments), and how it fits into the broader system of feed tuning. No gaps in understanding remain for the agent.

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?

The schema already provides 100% coverage of the three parameters with clear descriptions. The tool description does add meaning to the 'note' parameter by giving rich examples of acceptable plain-language formats, and explains the purpose of 'entry_id' and 'briefing_id' implicitly through the phrase about 'specific story' and 'which briefing.' However, with full schema coverage, a baseline of 3 is appropriate and the description's added value is marginal beyond the examples.

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 verb 'correct' and the resource 'briefing' explicitly, and gives concrete examples of plain-language inputs. It distinguishes itself effectively from sibling tools like 'tune_topic' or 'rate_briefing_entry' by positioning itself as the main way to retune a news feed via conversational feedback.

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 clear context for when to use this tool — to give free-form, plain-language correction to a briefing. It does not explicitly list alternatives or when not to use it (for example, if the user wants to set a specific topic weight without natural language, they might use tune_topic instead), but the phrase 'main way a person retunes their news feed by talking' strongly implies this is the primary conversational interface.

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