Get Look Ahead Data

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds valuable behavioral context: company_id defaults to the value from procore_set_config when omitted, group_id must identify an existing parent record, pagination via page/per_page with remaining pages reported, and specific error handling for 401/403/404. It also confirms 'Read-only — it changes nothing in Procore,' consistent with the annotations.

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 moderately sized but well-structured: it opens with purpose, then usage variants, parameter defaults, output format, safety, error codes, and API endpoint. Each sentence adds value, though some details (like the full endpoint) could be trimmed without loss of core guidance.

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?

Given 14 parameters and no output schema, the description covers purpose, scope, use case, prerequisites, defaults, pagination, safety, and failure modes. It adequately states it returns a JSON array of look ahead data without listing fields, but this is sufficient for an agent to invoke the tool correctly since key resolution and error handling are well explained.

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?

With 100% schema coverage, the description adds meaningful semantics for required parameters: company_id's default behavior and group_id's requirement to reference an existing parent record resolved via a list tool. It also explains pagination parameters (page/per_page and remaining pages), which goes beyond the schema's basic descriptions.

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 explicitly states it 'Fetches the Look Ahead report which provides future assignments and availability details for People within a specified Group.' This uses a specific verb (fetches), a resource (Look Ahead report), and a scope (specified Group), clearly distinguishing it from sibling lookahead tools that focus on scheduling rather than workforce planning 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?

It provides clear usage context: 'Use this to discover look ahead data or to look up the id of one before calling a tool that needs it,' and explains how to span all Groups with 'all'. It also gives prerequisites (resolve group_id with the matching list tool first), but does not name an explicit alternative tool, which would make the guidance more direct.

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