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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description must carry the behavioral weight, and it discloses a genuinely non-obvious gate: the paid-tier requirement for setting new text versus free removal. It still omits whether changes apply to already-scheduled posts or whether the route must be paused, and its stated «до 1000 знаков» conflicts with the schema's 4000-character limits.

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 compact sentences, front-loaded with the purpose and a concrete example, followed by the tariff constraint and the format note. Every sentence addresses a distinct concern, though the trailing character limit adds confusion rather than value given its conflict with the schema.

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 three-parameter mutation with no output schema and fully documented parameters, the description supplies purpose, the paid-plan gate, and the lightweight markup conventions. What is missing is the effect on existing or scheduled content and the expected response, but the core calling information 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 description coverage is 100%, so the baseline is 3, but the description's one parameter-relevant claim — that text is limited to 1000 characters — contradicts the schema, which sets maxLength 4000 for both textBefore and textAfter. Rather than adding correct meaning beyond the schema, it introduces a conflicting constraint that could cause an agent to truncate valid input.

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 opens with a specific verb and resource: it sets the text that appears before and after the copied post, illustrated with a concrete example («Новый пост в нашем канале»). The concept of frame text is distinct enough from siblings like route_set_replacements or route_set_utm, but the description never names or contrasts those siblings, so it stops short of full disambiguation.

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?

There is no explicit when-to-use statement or named alternative, but the tariff clause gives a real precondition for use: removing text works on any plan while setting new text requires a paid plan. An agent can infer the calling context, yet nothing tells it when to prefer this over route_set_replacements or route_set_utm.

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