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

The description adds substantial value beyond the annotations: it discloses that no change occurs until a human approves in Settings > MCP and execute_approved_action is called, and that approval requirements are admin-configurable. Annotations already flag destructiveHint=true, so the remaining gap is partial-update semantics — whether omitting a field in the data object leaves it unchanged or nulls it.

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?

Purpose is front-loaded in the first two sentences, and the approval sentences are dense but earn their space by describing a non-obvious gating mechanism. The long approval sentence could be split, but there is no filler.

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 approval workflow — the hardest thing for an agent to infer — is covered thoroughly, and an output schema exists so return values need no explanation. What is missing is the shape of the nested data object and partial-update behavior, which matters for a destructive mutation with a nested schema and zero parameter descriptions.

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 nested data object exposes seven writable fields (email, notes, phone, title, company, firstName, lastName) with no descriptions at all. The description says only 'Edit contact details' and never names those fields, explains that firstName is the sole required member of data while others are nullable, or clarifies merge-versus-replace behavior — so it fails to compensate for the coverage 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?

States a specific verb and resource: 'Edit contact details' on RetailHardHat contacts records. That distinguishes it from create_contact, delete_contact, get_contact and list_contacts by implication, though it never names those siblings explicitly or confirms the resource scope beyond 'contacts records'.

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 opening clause gives a domain context ('when working with RetailHardHat contacts records in the connected organization') and the approval sentence communicates a real prerequisite: the call only stages the change and execute_approved_action is what applies it. However it never says when to prefer get_contact first to fetch current values, or when not to use it.

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