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

Annotations already establish that this is a mutating (readOnlyHint=false), non-idempotent, non-destructive, open-world call, and the description adds real value on top: it discloses the credit cost per call, the absence of a sections argument, that the backend schedules all available components, and that queued rows are reported rather than re-run. That is substantive behavioral context beyond the annotation flags.

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 dense sentences, front-loaded with the operation and its cap, followed by behavioral facts and the cost pointer. Every sentence carries information, though 'There is no sections argument' addresses a parameter that does not exist and is a slightly defensive use of space.

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 an output schema present, return values need not be enumerated, and the description still previews that per-company partial status is returned. Cost, batch limit, and mutation semantics are covered; the remaining gap is the missing distinction from enrich_companies and any failure/permission behavior.

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 50%: workspaceId carries a long, detailed schema description while companyIds has none. The description only restates the 25-item cap that maxItems already encodes and notes a missing 'sections' argument; it adds no input format or identifier guidance for companyIds, so it neither compensates for the gap nor wastes effort.

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 ('Start a full company refresh for up to 25 companies') with the batch limit inline. It is distinguishable from refresh_leads by resource, but it never contrasts itself with the closest sibling, enrich_companies, leaving the refresh-vs-enrich boundary to inference.

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 description gives a clear context (a full refresh, capped at 25) and explicitly routes the agent to campaignstack_estimate_cost to learn the credit cost before committing. However, it offers no when-not guidance or explicit comparison against enrich_companies or edit_companies, so selection among similar company tools remains implied.

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