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

Annotations already declare non-readonly, idempotent, non-destructive, so the description doesn't need to restate safety. It adds genuinely new behavior context: partial-update semantics and the reason for them (settings made by hand are not undone), plus a caution that can_edit_access_rights is not the Admin role. It does not say what a successful call returns or how invalid keys are handled, which keeps it short of a 5.

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 sentences, front-loaded with the core action, then the boundary and the patch rule. The dash-and-parenthetical enumeration of powers is denser than it needs to be but every clause carries information; nothing is 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 17-parameter mutation with no output schema, the description covers the two things that matter most: what class of setting this touches (powers, not table rights) and how partial payloads behave. Remaining gaps are per-flag meanings and any confirmation of return behavior, which are secondary for a call an agent makes after reading the schema.

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 only 41%, and roughly half the 17 booleans (create_maps, create_charts, files_enabled, create_portals, can_delete_files, create_calendars, create_newsletters, allow_to_create_apps, access_to_only_own_files) have no schema description. The prose enumerates several of these powers, but only in aggregate ('create portals, charts, maps, calendars, mailings, work with files'), leaving the create_* flags and allow_to_create_apps/access_to_only_own_files ambiguous. It compensates partially, not fully, for the low coverage.

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?

States a specific verb and resource ('Change a team group's POWERS (and its name)') and immediately distinguishes the concept from table-level rights, pointing at set_table_permission as the different tool for those. An agent can separate this from create_team_group or set_user_role without opening the schema.

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?

Explicitly names the adjacent-but-different tool (set_table_permission) and the concept boundary, and gives an operative rule for invocation: 'Pass ONLY the keys that must change: keys not passed are NOT touched.' That is both a when-to-use and a how-to-use directive with a stated consequence.

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