Create or upsert a lead

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

Annotations only declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=false; the description goes well beyond that by disclosing required scopes, full_content data sensitivity, the idempotency-key retry contract, and the workspace-override behavior. The notable gap is upsert conflict semantics – what happens to tags/stage/fields when the lead already exists is never stated, which matters for an upsert. There is also mild tension with idempotentHint=false, but the description's explanation of the idempotency key plausibly reconciles it rather than contradicting it.

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?

Front-loaded with the core action, then scopes, then idempotency and workspace overrides in compact lines – each sentence carries information. Minor redundancy in restating the body's required fields already enforced by the schema.

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 mutation tool with a nested body schema, four parameters, and a sibling-heavy namespace, the description covers the invocation essentials: what to send, auth scopes, data sensitivity, retry safety, and workspace targeting. An output schema exists, so return values need not be explained; the only real omission is upsert/merge behavior on an existing lead.

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 75% and the schema already documents idempotencyKey and both workspace params, so the description largely restates ('Body requires channel and externalUserId', 'Provide idempotencyKey for safe retries'). It does add one piece of genuine meaning: workspaceId/workspaceSlug override the environment-configured default workspace, which is more than the schema's bare 'Optional Luca workspace id override'. Baseline 3 fits.

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 states a specific verb and resource ('Create or upsert a lead identity') plus the underlying operation (POST /api/leads), so an agent immediately knows what it does. The 'create or upsert' framing also implicitly separates it from luca_leads_update and the import tools, though no sibling is named 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?

Usage is implied by the operation and by the stated prerequisites: leads:write scope, luca:draft OAuth scope, and an Idempotency-Key. However, there is no guidance about when to prefer this over luca_leads_import_apply, luca_leads_identities_attach, or luca_leads_update, which share overlapping surfaces in a very crowded leads sibling set.

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