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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the negation of writes is largely redundant reinforcement. The description adds no failure behavior (invoice not found), no auth requirements, and no indication of what the payload contains, which annotations alone don't cover.

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 clauses: the operation and its non-goals first, the endpoint second. Every phrase carries information and nothing is buried or repeated.

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?

For a single-parameter read with full annotation coverage and no output schema, this is nearly sufficient — the agent knows it is a safe, targeted read. The only real gap is return-value shape and not-found behavior, which the description leaves entirely to inference.

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?

One required parameter with 0% schema description coverage, yet the description maps invoice_id onto the {Invoice-Id} path segment, conveying that it is an identifier rather than a filter. It adds no further semantics such as format hints (the numeric pattern lives only in the schema) or whether it is a RepairDesk internal ID.

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 ("Read a single invoice") and the explicit HTTP path GET /invoices/{Invoice-Id}, which unambiguously separates it from a listing operation. It stops short of naming the sibling repairdesk_list_invoices, so the single-vs-many distinction is only implicit.

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?

"Read a single invoice" implies the use case when an ID is already known, and "no payment or invoice creation occurs" bounds the scope. However, it never states when to prefer repairdesk_list_invoices or repairdesk_get_invoice_due over this tool, leaving the agent to infer the routing.

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