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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false. The description adds genuinely new context: the call is asynchronous, returns a run_id immediately, must be polled, and burns 100 credits. It stops short of stating that re-running spawns a new billable run (relevant given idempotentHint=false).

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?

Two dense sentences, front-loaded with the action and scope, then the async contract and the price. No clause is filler.

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 no output schema, the description correctly carries the essential return contract (run_id + polling) and the credit cost. Minor gaps remain around runtime expectations and whether repeated invocations incur additional charges.

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% and the description only restates the schema's own note that config.company_domain improves grounding, adding no format or syntax detail. It also says "one company" while the schema permits a deal, property, or market category as target, slightly narrowing the parameter's stated meaning.

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?

Specific verb and resource: "Run Company Intelligence (CI, 5 agents) on one company" plus the output dimensions (competitive landscape, threats, positioning). It does not, however, contrast itself with near-neighbors like competitive_intelligence or company_snapshot, so an agent must infer which one to pick.

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 explicit post-call workflow ("poll check_report_status until completed") and a cost signal (100 credits), which is real guidance. But it never says when to choose this over the sibling intelligence tools or when not to use it, so usage is only implied.

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