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

Annotations already flag a non-read-only, destructive, non-idempotent mutation, and the description adds genuinely new behavior: the approval gate, the fact that org admins can configure MCP approval requirements while business workflow approvals always apply, and the constraint that storage identity is immutable. It stops short of stating update semantics (partial vs. full replace of the nested data object) or what a destructive metadata overwrite means in practice.

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 approval and immutability constraints are front-loaded and earn their place, but the first sentence is product-boilerplate ('working with RetailHardHat documents records in the connected organization') that adds no decision-relevant information. Removing it would tighten the definition without losing meaning.

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?

An output schema exists, so return values need not be explained, and annotations plus the approval narrative cover the safety profile well. However, for a nested-object mutation the description omits which fields are updatable and whether omitted fields are preserved or cleared, which is the main thing an agent still needs before calling it.

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 description coverage is 0% and the tool has three required parameters plus a nested `data` object with an enum (`documentType`), yet the description names no parameters and never says which metadata fields are editable. The word 'metadata' is the only hint toward `data.name`, `notes`, `fileSize`, or `documentType`, so it fails to compensate for the schema gap.

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 gives a specific verb and resource ('Edit permit document metadata') and adds a distinguishing boundary: it 'cannot replace its storage identity', which separates it from attach_permit_document and delete_permit_document. The opening sentence ('Use this when working with RetailHardHat documents records in the connected organization') is generic filler that does not sharpen the purpose.

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 clearly states the critical usage condition: no change takes effect until a human approves the exact request and execute_approved_action is called, so an agent knows this is a staged, non-immediate write. It does not explicitly name alternatives (e.g., attach_permit_document to replace a file, update_permit for the permit itself), leaving sibling routing to inference, and the 'when working with... documents records' clause is too vague to count as guidance.

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