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

Adds substantial context beyond the annotations: returns only a boolean success flag and no visible ticket id, requires confirmed=true, and explains the optional X-HGR-Client header and the human vs ai_chat actor semantics. It does not address why destructiveHint=true is set or warn that a non-idempotent create will duplicate tickets on retry, which is the one behavior an agent most needs to know.

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?

Key information is front-loaded, but the text is padded with boilerplate ('Dedicated HGRApi tool for POST...', 'This is an explicit tool with a fixed endpoint; it is not a generic endpoint caller', 'Search terms: helpcentre contact') that adds little for tool selection. The dense metadata block is efficient but reads like generated documentation rather than guidance.

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?

Covers the essentials for a mutation tool: what is created, what is returned (boolean only), what is not returned (ticket id), the confirmation requirement, and scope. The remaining gap is retry/idempotency behavior for a non-idempotent create, which matters given destructiveHint=true.

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 100%, so both parameters are already documented and the baseline is 3. The description does add real meaning for the body by naming ContactModel's main fields (Message, Attachments) and the header handling, but it leaves the confirmed gating rule largely duplicative of the 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 (POST api/HelpCentre/Contact, creating a help-centre contact ticket) and explicitly disclaims being a generic endpoint caller. The domain/entity/operation metadata (support, support_ticket, create) lets an agent place it precisely relative to siblings such as hgr_create_support_ticket or hgr_reply_support_ticket.

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?

Gives an explicit use case (legacy contact form submissions where a visible ticket id is not required) and an exclusion rule (AIChat must prefer Contact2 when a ticket reference/link is needed). The only weakness is that the named alternative, Contact2, does not appear in the sibling list, so the agent cannot actually route to it.

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