Добавить участника или изменить его права

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

The description adds meaningful behavioral context beyond the annotations: it discloses that the tool operates on already registered users and that the 'member' parameter switches behavior from add to update. It also mentions 'точечные права поверх роли' (granular permissions on top of role), which hints at permission layering. However, it does not mention the replace-semantics of permission lists (though the schema does), nor does it elaborate on edge cases like duplicate adds or missing required fields. Given annotations already indicate a non-read-only, non-idempotent, non-destructive write operation, this is sufficient.

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 succinct: three sentences that cover the primary modes and the alternative tool. It is front-loaded with the main action and avoids redundancy with the schema. Every sentence adds necessary information with no filler.

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 7 optional parameters and no output schema, the description gives enough high-level context to understand the two main workflows. It correctly points to invites_create for unregistered users. However, it does not address what happens when no parameters are supplied (e.g., potential error) or provide a fuller picture of the permission arrays' effect, though those are partly in the schema. The description is slightly above average but not exhaustive.

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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining the conditional interplay between 'member' and 'email': without 'member', email identifies the person to add; with 'member', that parameter identifies whom to modify. This relational context is not explicit in the individual parameter descriptions, thus improving comprehension.

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 tool's function: adding a registered person to a case by email (without the 'member' parameter) or changing an existing member's role and permissions (with the 'member' parameter). It uses specific verbs ('adds', 'changes') and references the resource ('case', 'member'). It also distinguishes itself from sibling tools by explicitly naming invites_create as the alternative for unregistered users.

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 provides clear guidance on when to use this tool versus alternatives: it specifies that the tool works only for already registered users, and if the person is not registered, the user should use invites_create. It also explains the two modes of operation (add vs. update) based on the presence of the 'member' parameter, which serves as a usage decision tree.

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