Screen a list of companies

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

Beyond the readOnly/ openWorld/ idempotent annotations, the description discloses key behaviors: ambiguous names go under unresolved with candidates, rate-limit skips go under not_screened with reasons, rows carry only signal codes, officers are excluded by default because of extra request cost, and sections_used reports what signals could see. This gives the agent a full model of how results and limits are represented.

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?

The description is longer than average, but every sentence earns its place by covering a distinct behavioral or usage fact: batching cost, result rows, unresolved handling, not_screened handling, signal codes, officer defaults, and sections_used. It is front-loaded with the most important usage rule and avoids fluff or redundant restatements of the schema.

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 tool with this complexity (batch input, multiple opt-in flags, ambiguous matches, rate-limit constraints, output codes), the description covers all operational concerns: limits, defaults, cost implications, edge cases, and how to get detail. Since an output schema exists, the job of explaining return values is largely covered, and the description still adds useful context like signal-code behavior and sections_used.

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 100%, so the baseline is 3. The description adds genuine semantic value for include_officers by tying it to specific signals (no_active_officers, recent_officer_departures) and explaining the default-off behavior and extra request cost. It also clarifies the companies parameter semantics implicitly by describing mixed names/numbers and the 50-cap, though the schema already covers the format.

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 a precise scope: 'MORE THAN ONE company — a list, a comparison, "which of these", a batch from procurement'. It names the resource (companies), the action (screen), and the output shape (one row each: status, age, signals). It also explicitly contrasts with company_snapshot for single-company detail, making the purpose unmistakable.

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 direct usage guidance: prefer this over repeated company_snapshot calls because it costs a quarter of the requests and returns a glanceable table. It also tells the agent when to fall back to company_snapshot ('call company_snapshot on one company number for the detail behind them'). This is explicit when-to-use and when-not-to-use guidance.

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