List Budget Change Summaries

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

Annotations already declare readOnlyHint and idempotentHint, and the description appropriately reinforces safety with 'Read-only — it changes nothing in Procore.' It adds valuable context beyond annotations by detailing error responses (401, 403, 404) and the default behavior of project_id from procore_set_config, which helps the agent anticipate common failures.

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 compact and front-loaded with the core purpose, but it contains redundancy (e.g., repeating the required parameter and read-only nature already in annotations/schema) and an internal contradiction about single vs. multiple results. The API path and endpoint are useful, but the conflicting statements force the agent to reconcile inconsistent information.

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?

The description provides URL, error codes, and overall read-only behavior, but omits essentials for a list endpoint: pagination, filtering, sorting, and explanation of the 'full field set.' The return-type contradiction ('single JSON object' vs. 'list of rows') leaves the agent uncertain about the response shape. Since there is no output schema, the description must carry this burden but does not adequately do so.

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%, providing descriptions for both parameters, so the baseline is 3. However, the description introduces a contradiction by saying project_id 'defaults to the value set by procore_set_config when omitted' while the schema marks project_id as required. It also fails to mention exclude_custom_fields at all, leaving the agent without an explanation of its performance benefit beyond the schema's bare description.

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 'Return a list of budget change summary rows,' which clearly names a verb and resource. However, it later says 'Returns a single JSON object describing the budget change summary,' contradicting the list semantics. The phrase 'Use this when you already know which budget change summary you want' also suggests a single-item lookup, which muddies the purpose and fails to distinguish it from a show-type tool.

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 offers a condition for use ('when you already know which budget change summary you want and need its full field set'), but this conflicts with the list nature of the operation. It does not mention when not to use it, suggest sibling tools like list_budget_view_summary_rows or show_budget_modification, or clarify the role of the optional exclude_custom_fields parameter.

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