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

Annotations already declare this as a safe read (readOnlyHint=true, destructiveHint=false), so the bar is lower; the description still adds real behavior: results are capped at one page (paginating cursor exists in the schema but the cap is a behavioral fact), the search is scoped to a single division, and it requires a Cotlet API key with access to this app. It omits nothing critical, though it doesn't explain ordering or matching semantics.

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?

Five tight sentences, front-loaded with what the tool is before moving to usage, follow-up and prerequisites. Each sentence carries distinct information; 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?

There is no output schema, yet the description tells the agent what a result contains (name, code, city, status), the page-size limit, the empty-result meaning, and the auth requirement. Everything needed to call it correctly and interpret the response is present.

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 query, limit, cursor and division are all documented in the schema itself. The description confirms the query matches name or code and that results come one page at a time, but adds no syntax, default or format detail beyond the schema, so the baseline 3 applies.

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?

Specific verb (searches) plus resource (relations = customers/suppliers) with the scope narrowing (one division, by name or code). It explicitly distinguishes itself from create_relation and ties its output to create_sales_invoice, so an agent can place it precisely among its Exact Online siblings.

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?

States the search input (name or code), the downstream use of a match's account_id as the customer of create_sales_invoice, and the follow-up when nothing is found ('An empty list means no relation matches, and create_relation can add it'). Alternatives and their triggering conditions are named explicitly.

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