mgmt_grant_delete

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only says 'Delete grant' and provides a documentation URL. It does not disclose that this is a destructive operation, whether it requires special permissions, whether it is reversible, or what happens to the user's access. The URL is not a substitute for behavioral transparency in the description itself.

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 extremely short, but it is not effective conciseness. It consists of a bare URL and a two-word phrase. It is under-specified rather than efficiently written. The URL is likely not useful to an AI agent and takes up space without adding semantic value.

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 destructive management tool with no annotations and no output schema, the description is severely incomplete. It does not explain what a grant is, which parameters identify the target grant, whether user_uid or user_login is required, or what the response looks like. The sibling list shows many grant-related tools, and this description does not help an agent understand the operation's scope or prerequisites.

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 schema already documents all four parameters: pretty, user_uid, counterId, and user_login. The description adds no parameter-level meaning beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting, though the description could have clarified which parameters identify the grant to delete (e.g., counterId plus user_uid or user_login).

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 is 'https://yandex.ru/dev/metrika/ru/management/ Delete grant'. It includes a URL and a terse phrase 'Delete grant'. The verb 'Delete' and resource 'grant' are present, but the description is mostly a URL with no explanation of what the tool does, what a grant is in this context, or how it differs from sibling tools like mgmt_grant_create, mgmt_grant_update, mgmt_public_grant_delete, or mgmt_my_grant_get. It is barely more than a tautology of the tool name.

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 guidance on when to use this tool versus alternatives. The description does not mention that this deletes a user's access grant to a counter, nor does it distinguish it from mgmt_public_grant_delete or mgmt_grant_update. An agent has no context for selecting this tool over siblings.

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