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

Goes far beyond the annotations: 100-lead cap, per-lead warnings when the email or LinkedIn identifier needed for a sequence step is missing, rejection semantics for running/closed campaigns with error=campaign_closed, absence of paid enrichment, and the GDPR note that lead data is not written to the change journal. This is exactly the behavioral context annotations cannot convey.

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 purpose and limit, then lead shape, then constraints. It is dense and multi-clause, and the data-protection sentence is more compliance boilerplate than invocation guidance, but nearly every other clause prevents a concrete failure mode.

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 6-parameter mutation tool with an output schema, the definition covers input shape, constraints, error paths, and even summarizes the return payload (added, skipped, leads_total_after, warnings). Only validate_only is left to the schema.

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 0%, so the description carries the burden and mostly does: it enumerates the lead object fields, the at-least-one-of email/linkedinUrl rule, custom {{variable}} naming constraints, and explains deduplicate, allow_running_campaign and workspace. validate_only is never mentioned, leaving one of six parameters 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?

States a specific verb and resource ('Leads zu einer lemlist-Kampagne hinzufügen') plus a hard scope limit ('max. 100 je Aufruf'). It is clearly distinguishable from siblings like lemlist_list_leads or lemlist_search_people, the latter being named as a source of linkedinUrl values.

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?

Gives concrete usage conditions: LinkedIn-only sequences only need linkedinUrl, running campaigns are rejected unless allow_running_campaign=True, archived/closed campaigns always fail, deduplicate=True rejects leads already in another campaign. No explicit routing to an alternative sibling, but the when/when-not rules are unusually complete.

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