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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The phrase 'fields to change' usefully implies a partial update where unlisted fields are preserved, but the description never states that explicitly nor mentions any permission or irreversibility caveats.

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?

Two short sentences, action stated first, no filler. Every clause carries information about invocation.

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 nested `fields` object has no key enumeration in the schema, and the description only offers three illustrative names, leaving the valid field vocabulary largely unknown. Acceptable for a simple two-param tool with full annotation coverage, but not complete given the open-ended nested payload.

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 coverage is 100%, so baseline is 3, and the description earns an extra point by naming example field keys (firstName, lastName, email) for the free-form `fields` object, which the schema leaves as an unconstrained additionalProperties map.

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 + resource ('Update a contact by ID'), which is enough to separate it from read siblings like directiq_get_contact and directiq_list_contacts. It does not explicitly name a sibling alternative, so it stops short of a 5.

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?

'Provide the fields to change' tells the agent what to supply but not when to choose this tool over alternatives such as directiq_write_request or directiq_create_list. There are no preconditions, no when-not guidance, and no pointer to a sibling.

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