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

Annotations only declare mutation/open-world/non-idempotent flags; the description adds the material context an agent actually needs: this is an async job that returns run_id rather than results, it must be polled, it consumes 100 credits, and it runs a 5-agent swarm. Cost and async polling behavior are not derivable from the annotations or schema.

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 tightly packed sentences with no filler; identity, mechanics, return contract, next step, and cost are all front-loaded in the order an agent needs them.

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 two-parameter, no-output-schema tool, the description covers what it does, what it returns, how to retrieve results, and what it costs — everything required to invoke and follow through correctly.

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 schema already describes both leaf parameters (target = company/deal/property/market category; config.company_domain = website host for grounding), giving 50% coverage. The description adds nothing about parameters, and the undescribed nested config wrapper leaves a modest gap, so baseline 3 is appropriate.

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?

Names the exact operation (full competitive-intelligence swarm on a company, 5 agents) and explicitly frames itself as an alias of company_intelligence, so an agent knows it is functionally identical to a named sibling. It also states the return value (run_id), the follow-up tool (check_report_status), and the price (100 credits).

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 clear operational sequencing: call this, then poll check_report_status with the returned run_id. The alias statement implicitly tells the agent this is interchangeable with company_intelligence, but there is no explicit when-not or alternative-selection guidance beyond that.

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