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

With annotations already covering the read-only/idempotent profile, the description still adds three concrete behaviors not in the structured data: empty q yields VALIDATION_ERROR, result rows omit the field sheet, and a no-match returns an empty list rather than an error. That is exactly the kind of context annotations cannot convey.

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?

Three short sentences, each carrying a distinct piece of information: what matches, how errors behave, and which sibling to fall back to. The core matching rule is front-loaded and nothing is padded.

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?

With no output schema, the description still tells the agent what rows look like (no field sheet) and what an empty result means, and pagination is covered by the schema. An agent has everything needed to call this correctly and to act on the result.

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 limit and cursor are already fully documented and the description rightly does not repeat them. It does add one real semantic layer the schema does not: the AND-across-words / OR-across-fields matching rule for q, which changes how an agent should construct the query.

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 ('Find generated e-invoices by text') and immediately defines the matching semantics (every word must match one of the document's text fields, e.g. invoice number, buyer name, buyer TIN). This clearly separates it from myinvois_invoice_read and myinvois_invoice_list, which are explicitly named as different operations.

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 explicit routing: use myinvois_invoice_read with the id when you need the field sheet, and use myinvois_invoice_list to browse the newest when a search returns nothing. It also states the precondition that an empty q is rejected with VALIDATION_ERROR, so there is no ambiguity about when to call it.

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