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

No annotations exist, so the description carries the full burden and does well: it discloses credit spend bounded by daily_discovery_budget_credits, daily recurrence, lead creation in the audience, and the approval prerequisite. It does not say what happens to already-discovered leads or counters when the config is changed, or whether the budget is validated against remaining balance.

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 short sentences, front-loaded with the highest-stakes fact (SPENDS CREDITS), then the approval gate, then the disable exception. Zero filler.

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 10-parameter mutation with nested objects, no annotations and no output schema, the description covers the decision-critical behavior but leaves most parameters unexplained and says nothing about what a successful update returns or verifies. Adequate to decide whether to call it, thin for calling it correctly with non-default config.

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 only 10% across 10 parameters, so the description must compensate. It adds real meaning only for daily_discovery_budget_credits (spend cap) and enabled (false disables), and otherwise defers entirely via 'Same args as preview_update_campaign_discovery', leaving search_source, max_leads_per_day, both nested search configs, search_interval_minutes and max_total_discovered undocumented.

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?

Specific verb + resource: 'Turn on or adjust automatic lead discovery', with scope details (runs daily, adds leads to campaign audience, cost impact). It is clearly distinguished from the sibling preview_update_campaign_discovery, which the description names explicitly.

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 gating rule: only call after the user approved the preview, and the named workaround for the exception ('Disabling (enabled=false) needs no preview'). An agent knows both when to use it and when it may skip the preview path.

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