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

Goes well beyond the annotations: it clarifies that despite destructiveHint=true nothing is deleted (content and location untouched, group persists even when empty), discloses permission requirements, and explains edge-case handling (skipped ids counted, non-member ids ignored). This is exactly the kind of nuance annotations cannot convey.

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?

Front-loads the core action and the key clarification (label-only removal) in one dense sentence, then adds routing and permission in a second. Every clause earns its place, though the long parenthetical chain makes it slightly heavy to parse.

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?

Covers purpose, the alternative tool, permission requirement, and id edge cases for a two-param mutation with full schema coverage and an output schema that handles return values. The only missing element is any mention of scale/rate considerations for the 5000-id upper bound.

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 both parameters are already documented with id prefixes and list/range constraints; the description adds only the `skipped` outcome vocabulary. Baseline 3 is appropriate when the schema carries the parameter burden.

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+resource ('take screens out of a screen group') and immediately disambiguates the scope of the mutation: only the label drops, the screens and their location remain. It also names the inverse sibling (add_screens_to_group), so an agent can pick between the two without inspecting schemas.

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?

Gives explicit routing to the alternative ('To add screens use add_screens_to_group') and states the required permission (`screen.edit`), plus how out-of-reach and non-member ids are handled. It lacks an explicit 'do not use this when...' clause, which is the only gap.

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