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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered, yet the description adds genuinely useful behavior: hidden constants (keys, passwords) come back with no value, and a same-named scenario constant overrides the bot constant. That is exactly the kind of caveat an agent cannot get from annotations. It stops short of describing the response shape or ordering.

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 tight sentences, each carrying distinct information: what bot constants are and how they are referenced, override precedence, and the hidden-constant caveat. No filler, and the core definition is front-loaded. It could still open with an explicit 'returns the list of' to lead with the action.

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 two-parameter read tool with full schema coverage and no output schema, the description covers the essentials, including the important fact that hidden constant values are withheld. Missing only minor framing such as the fact that the result is a list and whether ordering or scope (own bot only) matters.

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 withUsage parameter is well documented in-schema, including the usedIn/overriddenIn fields and the warning that those lists are empty without it. The description adds no parameter-level meaning at all, so 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?

The description names the resource precisely (bot-level constants shared across all scenarios of the bot) and gives concrete examples of what they hold (phone, address, hours). It also distinguishes bot constants from scenario-level constants by precedence, which helps separate it from the set/delete siblings. The only gap is that it never uses an explicit action verb like 'return a list', leaving the read action 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?

There is no when-to-use guidance and no alternative named — nothing tells the agent when to call this versus the scenario-level constant tools or chatbot_show. The only usage-flavoured sentence ('подставлять её можно только в запрос к сервису') is about how the returned values may be used downstream, not about when to select this tool.

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