Update Tax Type

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

Annotations already indicate the tool is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds value by explaining that 'only the supplied fields are changed', implying a partial update (PATCH behavior), and that the modified object is returned. This goes beyond annotations. However, it does not mention any authorization requirements or potential side effects.

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 four sentences long. It starts with purpose, then usage, then a note on required fields, and ends with technical endpoint info. While there is no wasted text, the inclusion of the Procore API class and endpoint may be unnecessary for an AI agent that would use the tool via the server. It could be slightly more concise.

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?

For an update tool with fully described schema and no output schema, the description provides sufficient context: what the tool does, which fields are modified, what is returned. It lacks details on error handling or permission requirements, but overall it is adequate for an AI to invoke correctly.

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 input schema has 100% description coverage for all 6 parameters. The description only reiterates the required parameters (id, company_id) without adding deeper semantic meaning beyond what the schema provides. For example, 'origin_data' is described in the schema as 'additional Third-party Metadata' but the description adds nothing. Given high schema coverage, baseline is 3.

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 action ('Update a Tax Type's attributes') and the resource ('Tax Type'). It uses specific verbs like 'update' and 'returns the modified object'. While the name itself is clear, the description reinforces it. Among hundreds of sibling tools, the purpose is distinct enough, though no explicit sibling differentiation is provided.

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 says 'Use this to update an existing Tax records' which provides basic usage context but lacks guidance on when NOT to use this tool or which alternative tools (e.g., create_tax_type for creation, delete_tax_type for deletion) might be more appropriate. No exclusions are stated.

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