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

Goes well beyond the annotations by disclosing credit consumption ('reserves 2 credits'), partial-failure semantics ('Saves the action even when brief generation fails'), and a hard scope boundary ('Does not publish content'). Annotations already cover the safety profile (readOnly false, destructive false, idempotent true), so the remaining gap is what 'reuse' matching actually keys on and what the call returns.

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?

Four short sentences, front-loaded with the core action and with no filler or repetition. Density is high; the only weakness is that the 'create or reuse' distinction, which drives the idempotent behavior, is never unpacked, leaving a loaded phrase unclarified.

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 six-parameter mutation with no output schema, the description covers the essentials an agent needs: credit cost, that the action persists even on brief failure, and that nothing is published. It leaves the nature of the created object and the meaning of 'reuse' unexplained, which matters for predicting the effect of a call.

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 50% schema coverage, the description usefully adds meaning to generateBrief (billing consequence of 2 credits and a customer-request precondition) that the schema's 'queue a brief using content credits' does not convey as sharply. The other parameters (promptId, title, description, targetUrl, acknowledgedHighStakes) get no added semantics, though three are self-describing identifiers and two are documented in the schema.

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 ('Create or reuse an action from a tracked prompt') plus a scope boundary ('Does not publish content'), so an agent knows it produces an action record, not a draft, brief, or publication. It does not name the sibling it is distinguished from (e.g. start_action_draft, generate_action_brief), so sibling differentiation is left implicit.

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?

Gives one explicit conditional rule for a parameter ('Only set generateBrief when the customer requests metered brief generation') and a scope exclusion ('Does not publish content'). It never states when to call this tool versus the many action-related siblings, so the when-to-use-this-vs-alternatives guidance is only implied.

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