List Calendars (V2.1)

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

The description adds valuable behavioral context: company_id/project_id defaulting from procore_set_config, error statuses (401/403/404), read-only nature, and V2.1-specific interval behavior. Annotations already declare readOnlyHint=true and idempotentHint=true, and the description's 'Read-only — it changes nothing in Procore' aligns. However, the claim 'Returns a single JSON object describing the calendar' is likely inaccurate for a list endpoint and is not clarified by annotations, reducing overall transparency.

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 a dense paragraph that front-loads the primary purpose but then mixes in usage guidance, default behavior, error handling, and endpoint details. It includes a contradictory statement about returning a single JSON object, which adds confusion. While concise in word count, the structure is not well-organized and some sentences could be removed or clarified.

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?

Despite the rich annotations and complete schema, the description fails to clarify the return shape (list vs single object), pagination behavior, or how filters apply. For a list endpoint, this is a critical gap. The mention of 'single JSON object' is especially problematic and could lead an agent to incorrectly invoke the tool when it meant to retrieve one calendar rather than list many.

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 description coverage is 100%, so each of the 8 parameters already has a clear description. The description adds defaulting behavior for company_id and project_id and notes they are required, which is useful. However, it doesn't elaborate on page, sort, per_page, or filters beyond what the schema provides, so the description does not significantly augment the schema.

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 first sentence clearly states 'List all calendars in a project associated with the Scheduling/Programming tool,' which is a specific verb+resource. However, the subsequent guidance says 'Use this when you already know which calendar you want and need its full field set. Returns a single JSON object describing the calendar.' This contradicts the list behavior and makes it indistinguishable from the sibling tool get_calendar_by_id_v2_1, which is misleading.

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 provides some usage context: 'Use the Show Project API when you need the project time zone' and 'Use this when you already know which calendar you want and need its full field set.' However, the latter is more appropriate for a show/get endpoint than a list endpoint, creating confusion. No explicit when-not-to-use or alternative like get_calendar_by_id_v2_1 is mentioned, and the guidance is contradictory with the list purpose.

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