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

Annotations flag a non-read-only, non-idempotent, non-destructive mutation. The description adds value beyond that: it frames the call as an intent-gated trust action ('same trust level as clicking Approve in the dashboard'), which tells the agent not to invoke it autonomously. It does not cover reversibility or what the approval changes, so a 4 rather than 5.

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?

Three front-loaded sentences that each carry signal: what it does, when it is needed, and the intent guardrail. The Rebbel-dashboard comparison is slightly verbose but earns its place by anchoring trust level.

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-param, no-output-schema approval action, the description covers purpose, prerequisites, trigger conditions, and the caller-intent constraint. A brief note on what changes after approval (and whether it can be undone) would close 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 coverage is 100% and both params carry source hints (brandId from list_brands, strategyId from get_strategy). The description adds no parameter detail, so the baseline of 3 is appropriate when the schema does the work.

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 ('Approves a draft strategy') and, crucially, distinguishes it from generate_strategy (which may auto-approve) and generate_campaign (which depends on approval). An agent can tell exactly what this does and how it differs from the many sibling approve_* tools.

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?

Explicit when-to-use: only when generate_strategy failed to auto-approve on a thin/low-confidence website scan. It also states the downstream dependency (required before generate_campaign succeeds) and the intent gate (only call once the user actually wants it approved). This is a model routing instruction.

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