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

Despite annotations already marking the call as non-read-only and idempotent, the description adds meaningful behavior: it charges the company_refresh credit action, refunds on fetch failure, reuses an already-queued refresh at no charge, and routes through a globally paced queue so results are asynchronous. This is exactly the kind of side-effect and timing disclosure an agent needs.

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?

Three sentences, each earning its place: first defines the action and payload, second covers cost/refund/idempotency, third covers async behavior and read-back paths. The most decision-relevant fact (queue a fresh fetch) is front-loaded.

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 side-effecting async queue operation with no output schema, the description covers the essentials: what data will be produced, that it is not synchronous, that a duplicate request is harmless, what it costs, what happens on failure, and where to retrieve results. No critical decision or invocation detail is missing.

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?

The required companyId is not described in the schema, and the description only indirectly identifies it as the company whose LinkedIn page is fetched; the optional workspaceId is documented in the schema. The description adds little parameter-specific meaning beyond what the input schema and tool name already imply.

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 opens with the specific verb-object pair 'Queue a fresh fetch of a company's public LinkedIn page' and enumerates the data produced (headcount, follower count, firmographics, metric snapshot, growth/decline signals). This clearly differentiates the tool from read-only getters in the sibling list: it schedules a refresh rather than returning current data.

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 context is clear: use this when a fresh asynchronous fetch of company data is needed, and read the results later via campaignstack_get_company_metric_history or campaignstack_get_company. It does not explicitly state when not to use it or name alternative refresh/enrichment tools, so it stops short of a full when/when-not guide.

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