Заявки (лиды)

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

Annotations already mark the tool as read-only (readOnlyHint=true), so the description need not restate that. It adds meaningful behavioral detail: the precedence rule 'alert' overrides 'status' when both are specified, and each alert value is defined (e.g., overdue, trial_no_date). This goes beyond the schema's enum list, which only lists the values without semantics. The description does not contradict any annotation and provides context that affects how results are filtered.

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 a single, information-dense sentence that front-loads the purpose ('Список заявок с фильтрами') and then rolls out the alert specifics. Every clause adds value: the list of alert groups with parenthetical explanations is essential and not duplicated verbatim in the schema. There is no fluff, no repetition of annotations, and the structure is natural – a clear statement of function followed by detail.

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?

Given the tool's moderate complexity (5 parameters, no output schema), the description covers the most intricate part – the alert semantics and precedence – which is not in the schema. The other parameters (page, limit, status, owner_id) are self-explanatory via their schema descriptions, so the description need not elaborate. It lacks an explicit mention of pagination defaults or return format, but those are either in the schema or not required for calling the tool. Overall, the description provides enough for correct invocation without knowing the output structure.

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?

The input schema covers 100% of parameters, so the baseline is 3. However, the description enriches the 'alert' parameter by explaining each enum value in prose, something the schema does not do (the schema only says 'Проблемная группа; важнее статуса'). It also reinforces the precedence rule. This adds semantic depth for the most complex parameter, going beyond the schema's minimal descriptions. Other parameters (page, limit, status, owner_id) are adequately described in the schema, and the description does not need to repeat them.

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 action ('Список заявок') and the resource (leads), and further specifies filtering capabilities. It explicitly enumerates the alert groups and their meanings, making the tool distinguishable from siblings like get_lead (single lead) and search (free-text) without needing to inspect the schema. The inclusion of alert semantics adds precision beyond a generic list description.

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?

The description communicates that this is a filtered list tool, so an agent can infer when to use it for querying leads by status or problem groups. However, it does not explicitly state when to avoid it (e.g., for free-text search use 'search', for a single lead use 'get_lead'), nor does it mention any exclusions or alternatives. This leaves the routing decision to inference from sibling names, which is adequate but not fully explicit.

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