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

Annotations already state this is a write operation (readOnlyHint=false). The description adds useful behavioral context by revealing the tool can either create new records or link to existing ones, and that it operates on private, campaign-attribution data from allowlisted payloads. It does not disclose duplicate handling, idempotency behavior, or authorization requirements beyond 'allowlisted.'

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?

A single, efficient sentence that front-loads the action and outcome and contains no filler. It conveys the core function without redundant restatement of the tool name.

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 write tool with a complex nested payload, four parameters, and no idempotency annotation despite an idempotency_key parameter, the description is too sparse. It does not explain what 'link' means, what happens on duplicate leads, how idempotency_key works, or what the output schema returns.

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 0%, so the description needed to clarify the parameters. It indirectly identifies campaign_id and lead_payload via 'campaign-attribution' and 'allowlisted lead payload', but it leaves project_id and idempotency_key unexplained and does not describe which fields are required or how the payload is validated.

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 names a specific action ('Create or link') and a specific resource ('private campaign-attribution and CRM lead records'), and narrows the source to 'an allowlisted lead payload.' This makes the tool's intent clear, though it does not explicitly differentiate it from crm.create_lead, which also deals with CRM lead records.

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?

Usage context is implied by terms like 'campaign-attribution' and 'allowlisted lead payload', suggesting this is for campaign-sourced lead ingestion rather than manual CRM lead creation. However, there is no explicit when/when-not guidance or mention of alternatives such as crm.create_lead, so the agent must infer the right selection.

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