Create Productivity Log

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

The description adds significant behavioral detail beyond the annotations: it explicitly states non-idempotency ("calling it again creates another record"), describes the success response (HTTP 201 with new id), and enumerates common failure statuses (401, 403, 404) and their meanings. Also notes project_id defaults from procore_set_config. This goes well beyond the structured annotation hints.

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 unnecessarily long and poorly structured, with markdown headings, bullet points, and scattered information. Key details like the container of Line Item ID instructions are placed in the middle, and the description repeats the create action later. It would benefit from briefer, more front-loaded phrasing.

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 its verbosity, the description covers all essential usage aspects: purpose, required parameters, project_id default, the Line Item ID prerequisite and how to obtain it, response behavior, error handling, and the API endpoint. The link to the Daily Log guide fills the gap for attachment details. For a tool with a nested object and no output schema, this is fairly complete, though it could be tighter.

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 already describes both parameters with 100% coverage, but the description adds meaningful context: it explains that project_id defaults to procore_set_config when omitted, and it provides guidance on the required Line Item ID within the productivity_log body, which is not detailed in the schema (additionalProperties is true). This compensates for the schema's lack of nested field detail.

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 clearly states "Creates single Productivity Log" and later "Creates the productivity log and returns it with its new id (HTTP 201)", unambiguously indicating a create operation. This distinguishes it from sibling tools like list_productivity_logs, update_productivity_log, and delete_productivity_log, which are all present in the sibling list.

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?

Provides clear context that this tool is for creating new productivity logs, not updating or listing. It details prerequisites (Line Item ID from an approved contract) and explains how to find that ID using other endpoints. It does not explicitly name alternative tools for non-create operations, so it stops short of full when/when-not guidance.

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