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

Goes well beyond the lone idempotentHint annotation: atomic failure ('a missing one is named and nothing changes'), ordering semantics for add, existing members keeping their place, removal being scoped to this study only with simulations and runs untouched, the public-study refusal rule, and the auto-grouping side effect. This is exactly the kind of context an agent needs before a mutation.

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 operation and prerequisites, then moves through ordering, side effects, restrictions, and return fields in a logical sequence. Dense but every clause carries information; a few parenthetical asides make sentences long, keeping it short of a 5.

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?

No output schema exists, yet the description spells out the return shape (study, added, removed, member_simulation_ids, archived_member_ids, app_url). Combined with atomicity, ownership, ordering, and side-effect notes, an agent has everything needed to invoke it correctly.

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?

With 100% schema coverage the baseline is 3, but the description adds real meaning: add appends in order and skips reordering for already-present members, remove detaches only from this study, and study_id should come from mcg_get_study. The maxItems=100 constraint is left to the schema, so not quite a top score.

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?

Opens with a specific verb+resource pair ('Add simulations to a study and remove them from it') that can be told apart from siblings like mcg_get_study or mcg_delete_study without opening the schema. Both directions of the membership operation are stated in the first sentence.

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 concrete prerequisites ('You must own the study... and every listed simulation') and points to mcg_get_study for obtaining the id. It also states a when-not condition (joining a public study is refused for a run that cannot be public). It does not name an alternative membership mechanism, though none exists among the siblings, so this is clear context rather than a complete when/when-not/alternatives treatment.

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