List Incident Alert Recipients

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

The description goes well beyond the annotations by disclosing pagination behavior ('page and per_page control pagination and the response reports how many pages remain'), default behavior for company_id (from procore_set_config), and error response details including specific HTTP status codes (401, 403, 404). It also explicitly states 'Read-only — it changes nothing in Procore,' reinforcing and adding context beyond the readOnlyHint/idempotentHint 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 multi-sentence but well-structured, leading with purpose, then usage, then behavioral details, then error handling, and finally API context. Each sentence contributes useful information, though the trailing 'Procore API: Project Management > Incidents. Endpoint: GET /rest/v1.0/...' is arguably supplementary and may be unnecessary for tool selection/invocation. It is not overly verbose, but contains a bit more than strictly needed.

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?

This tool has no output schema, so the description must explain return values. It explicitly states 'Returns a JSON array of incident alert recipients' and mentions pagination reporting. It also covers required parameters, default behavior, prerequisites, read-only nature, and likely error codes. Given the tool's moderate complexity and lack of output schema, the description is comprehensive enough for an agent to select and invoke it 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 input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds meaningful semantics beyond the schema: company_id 'defaults to the value set by procore_set_config when omitted' (not in schema), severity_level_id 'must identify an existing parent record — resolve it with the matching list tool first' (dependency not in schema), and it explains that page/per_page control pagination with a 'pages remain' indication (additional behavior not in schema). This raises the score to 4.

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 'Return a list of all Incident Alert Recipients associated with the specified Company and Incident Severity Level,' providing a specific verb (return/list), resource (incident alert recipients), and context (company and severity level). It also explains a primary use case ('discover incident alert recipients or to look up the id of one before calling a tool that needs it'), distinguishing this list tool from sibling show/create/delete tools.

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 clear when-to-use guidance: 'Use this to discover incident alert recipients or to look up the id of one before calling a tool that needs it.' It also advises resolving severity_level_id with 'the matching list tool first,' which is a helpful prerequisite. However, it does not explicitly state when NOT to use this tool (e.g., when a single recipient is needed, use show_incident_alert_recipient), so it falls short of full exclusion guidance.

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