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

Annotations already flag destructiveHint=true, readOnlyHint=false and non-idempotent, but the description adds the genuinely non-obvious trait: writes are staged and require human approval plus a separate execute_approved_action call, with admin-configurable approval requirements. It still doesn't disclose whether `data` is merged or replaces existing fields, or what specifically gets overwritten.

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?

Four sentences, well front-loaded with the action first and the approval gate immediately after. The lead-in 'Use this when working with RetailHardHat sites records in the connected organization' repeats the title and could be cut, but nothing else is wasteful.

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 output schema and annotations cover return values and the safety profile, and the approval workflow is explained. The gap is update semantics: for a destructive, non-idempotent mutation over a wide optional field set, the agent still doesn't know partial-vs-full replacement behavior.

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 `data` is a ~30-field nested object, so the description must carry the load – but 'Update allowed fields' never identifies which fields are allowed, whether unspecified fields are preserved, or how `id` is sourced. Minimal compensation for a very rich schema.

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?

States a specific verb and resource ('Update allowed fields of site'), which clearly separates it from update_project, update_task and other update_* siblings. The opening 'working with RetailHardHat sites records' is filler and the 'allowed fields' qualifier is never resolved, but the core action is unambiguous.

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 gives a critical usage condition – nothing changes until a human approves in Settings > MCP and execute_approved_action runs – which tells the agent about a required follow-up step. However, it never says when to pick this over adjacent siblings like set_site_custom_field, update_site_document, or update_site_team_member, and gives no exclusions.

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