mgmt_filter_get

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it discloses almost nothing. It does not state that this is a read-only retrieval, what the response contains, whether authorization or OAuth scopes are required, or any error/edge-case behavior. 'Get' weakly implies non-destructive behavior, but the description adds no context beyond what the tool name already conveys.

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 core phrase is appropriately short and front-loaded, but the leading documentation URL ('https://yandex.ru/dev/metrika/ru/management/') does not earn its place and adds noise for an AI agent. The description is not verbose, but its structure is undermined by a non-functional prefix that offers no callable 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?

For a tool with 4 parameters, no output schema, no annotations, and roughly 50 similar siblings (goal_get, operation_get, segment_get, counter_get, etc.), the description is under-specified. It does not explain what a filter is, what the response looks like, or any constraints on counterId/filterId. An agent could call it correctly from the schema alone, but nothing helps it confirm it selected the right tool beyond the name.

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% — counterId, filterId, pretty, and callback all have descriptions in the schema. The tool description adds no parameter-level meaning, so the schema does the heavy lifting. Baseline 3 applies because the description neither compensates for missing coverage nor adds value beyond the schema, but also doesn't conflict with 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 states 'Get filter by ID' — a specific verb (get) and resource (filter) with the retrieval key identified. This clearly maps to the mgmt_filter_get tool and contrasts with sibling filter tools like mgmt_filters_list, mgmt_filter_create, and mgmt_filter_delete. However, it does not explicitly name or differentiate from any sibling, and the leading URL is documentation noise rather than purpose clarification.

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?

No guidance is given about when to use this tool versus alternatives. There is no mention of when to prefer mgmt_filter_get over mgmt_filters_list, no prerequisites (e.g., needing the filterId first from a list call), and no exclusions. The usage context is only weakly implied by the phrase 'Get filter by ID', which essentially restates the tool name.

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