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

Annotations already mark readOnlyHint=true and destructiveHint=false, which the description's 'Read-only' reinforces consistently. The description adds genuinely new behavioral context: a personal-data handling directive ('never repeat it into a post or an unrelated tool'), output shape, newest-first ordering, and the LinkedIn-epoch nuance for date filters.

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?

Single dense paragraph that front-loads the purpose before filtering details. The personal-data warning earns its capitalization, and the read-only/free note is a one-word add. Slightly long, but with 10 parameters and no output schema, every clause carries weight.

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?

With 10 optional parameters and no output schema, the description compensates well: it enumerates return contents (answers, campaign/creative, consents, test flag), ordering, filters, pagination, and data-handling constraints. The schema handles parameter documentation at 90% coverage. Minor gap: no pointer to get_linkedin_lead for single-lead lookups.

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 90%, so the baseline is 3. The description adds value on top: it flags that LinkedIn actually consumes epoch ms for since/until, explains that formId scopes to a specific form, and identifies start as the pagination parameter. Some params (leadType, adAccountId, pageId, formVersion) are left to the schema, which already documents them.

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: 'The LEADS a LinkedIn lead gen form collected.' It enumerates what each response contains (answers keyed by field, campaign/creative, consents, test-lead flag), which distinguishes it from siblings like list_linkedin_lead_forms (forms, not responses) and get_linkedin_lead (single lead). Ordering ('Newest first') adds further precision.

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?

Provides clear context for when to use it: retrieving responses from a LinkedIn lead gen form, with concrete filter scenarios (formId, since/until, testLeadsOnly) and a pagination instruction ('Pass start for the next page'). It does not explicitly name alternatives or state when not to use it, so it falls short of full routing guidance.

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