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

Annotations already declare destructiveHint=true, so the safety bar is partly covered; the description earns credit for going further by naming the specific action that is destructive and its blast radius ('clear_all deletes every lead on the agent'). It does not disclose whether individual deletes are recoverable, whether import actions overwrite existing leads, or any auth/permission requirements.

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?

Two sentences, zero filler: capability first, action enumeration second, safety warning last. Nothing could be removed without losing information.

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?

Annotations carry the mutation/safety profile and no output schema exists, so the description needn't explain returns. But with eight actions and 20% schema coverage, the description should have said which parameters each action expects; as written an agent must reverse-engineer the action-to-parameter mapping from the schema alone.

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 only 20% (groupId and rawText are documented in the schema itself), and the description does not compensate by mapping the remaining parameters to actions — lead vs leads, leadId vs leadIds, leadGroupId, and additionalInstructions are left for the agent to infer. For a 10-parameter, 8-action tool this is a material gap in knowing which fields are required for which action.

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 set and resource ('Create/update/delete/import CRM leads') and enumerates all eight actions, so an agent knows exactly what operations are reachable. It never explicitly contrasts itself with the sibling leads_read, relying on the naming convention for that differentiation.

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 action list implies when each operation applies, and the destructive note steers an agent away from clear_all in normal use. However, there is no explicit guidance on when to pick leads_write over leads_read, contact_leads, or lead_groups_write, and no per-action conditions such as when import_bulk is preferable to magic_import.

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