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

Annotations already declare readOnlyHint=true, but the description adds crucial behavioral context: the link must not be opened or tested because rewards depend on real couriers and machine transitions distort stats. It also clarifies that the application is filled on the service's site, not through the tool. This goes beyond the annotation and is essential for correct invocation.

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?

The description is efficient: it opens with the purpose, lists the return values, gives usage timing, and then provides critical warnings. Every sentence carries unique information—there is no fluff or repetition. The structure front-loads the core purpose and then layers operational 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?

With no output schema, the description compensates by detailing all returned fields (link, partnerLink, disclosure, page address). It also covers the workflow (pass link and disclosure to user, don't open it) and the boundary of the tool's responsibility (applications are not accepted). For a single-parameter tool, this is fully complete.

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%, and the single parameter 'service' is already described as a slug from list_services with an example. The description adds no additional parameter-level detail beyond referring to 'выбранный сервис,' which is already implied by the schema. Thus, it meets the baseline for well-documented schema but doesn't elevate it.

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?

The description clearly states the tool returns a link for a courier to apply to a chosen service, and enumerates the exact payload (link, partnerLink flag, disclosure text, page address). It distinguishes itself from sibling tools by specifying when it's called (after service selection) and what it does not do (does not accept applications).

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?

It explicitly states when to use: 'Вызывайте, когда человек уже выбрал сервис и хочет откликнуться.' It also gives clear exclusions: 'сам по ней не переходите и не открывайте её для проверки' and notes that applications are handled on the service site, not by КурьерHUB. This provides clear when-to-use and when-not-to-use guidance without needing to reference alternatives.

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