Get Company-Level Groups

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

The annotations (readOnlyHint=true, destructiveHint=false) already convey read-only safety, and the description redundantly restates this. It does add useful behavioral context about error payloads (401, 403, 404) and the default company_id behavior. However, the serious internal contradiction between 'all accessible groups' and 'single JSON object' obscures the actual response behavior, undermining 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 overly long and contains redundant (read-only statement already in annotations) and contradictory content. The conflicting 'all groups' vs 'single object' phrases could have been resolved in one simpler, clearer sentence. Useful endpoint information is buried in the clutter.

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?

There is no output schema, so the description must clarify the return shape, but the description contradicts itself (list vs single object). It does include an API endpoint and common error statuses, which are helpful. Yet without a clear statement of whether this returns a list or a single object, and how pagination/filtering affect the result, the tool cannot be reliably invoked.

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%, and each parameter has a descriptive comment, so the schema carries the main burden. The description adds the default behavior for company_id ('defaults to the value set by procore_set_config when omitted'), which is valuable beyond the schema. No other parameter semantics are explained, so the description contributes only marginal additional value.

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?

Although the description begins with 'Returns all accessible company-level groups with pagination and filtering,' it later states 'Returns a single JSON object describing the company-level group,' directly contradicting the list semantics. The usage line also says 'when you already know which company-level group you want,' further suggesting a single-item fetch. This internal contradiction makes the core purpose ambiguous and potentially 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 does provide a usage context: 'Use this when you already know which company-level group you want and need its full field set.' However, this guidance conflicts with the plural, list-oriented nature of the tool name and the first sentence. No alternatives are mentioned, and no explicit when-not-to-use criteria are given.

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