Sync ToDos (Deprecated)

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

The description adds substantial behavioral detail beyond annotations: partial update semantics ('Send only the fields you intend to change; omitted fields keep their current values'), success return behavior, and detailed error scenarios (401, 403, 404). This is particularly valuable given the absence of an output schema. It aligns with annotations (readOnlyHint false) and does not contradict them.

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 front-loaded with the purpose statement but contains redundant deprecation warnings: 'This endpoint has been deprecated' and 'DEPRECATED: Procore has deprecated this endpoint (as of 2021-03-31).' are repeated. While the content is logically ordered and each piece adds value, the redundancy makes it longer than necessary.

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 covers operation type, deprecation status, partial updates, error handling, and the exact endpoint. It lacks detail on the item structure of the updates array (schema leaves items empty) and does not provide a response example beyond 'the modified todo.' Given the tool's complexity and lack of output schema, this is reasonably complete but has notable gaps.

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 schema already provides basic descriptions for both parameters (project_id, updates) with 100% coverage, but the description enriches the 'updates' parameter by explaining partial-update behavior. It also lists required parameters. However, it does not clarify the structure of objects within the updates array (schema items are empty), leaving some semantics unresolved.

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 the tool's function: 'This endpoint creates or updates a batch of ToDos.' This is a specific verb+resource combination that distinguishes it from single-todo tools like update_todo or show_todo. It also explicitly labels the tool as deprecated and points to a replacement endpoint, eliminating ambiguity.

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 explicit deprecation guidance: 'Instead, use [/rest/v1/calendar-items)' and recommends using procore_search_endpoints to find newer versions. It implies batch usage but does not explicitly name sibling tools for single-todo operations (e.g., update_todo). The alternative is given as an endpoint rather than a tool name, which slightly reduces clarity for an AI agent navigating tool options.

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