update_entity_access

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the burden falls largely on the description, which usefully discloses a server-side validation rule (acl writes rejected while inheritance is active) — a genuine behavioral trait not derivable from the schema. It omits whether access changes are reversible or require elevated auth, keeping 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?

Two sentences, no filler, and the critical prerequisite is front-loaded in second position where an agent will read it before constructing arguments. Every clause carries distinct information.

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 mutation tool with a nested ACL object and no output schema, the description covers the two mutation modes and the key precondition. It stops short of describing failure modes (partial application when only acl is invalid) or what the caller gets back, which for a no-output-schema tool would be worth a clause.

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 75% and the schema already documents the acl grant/revoke/role shape and the '[] disables inheritance' semantics, so baseline would be 3. The description adds real value by stating the interaction constraint between permissionSources and acl (ordering prerequisite), which the schema cannot express.

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 ('Update extended access settings') and enumerates the two operations it performs (inheritance toggle via permissionSources, acl grant/revoke). It does not, however, distinguish itself from the near-twin sibling update_entity_permissions or from get_entity_access, so an agent must infer which access-mutation tool to pick.

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?

It gives one useful operational rule — 'Disable inheritance first — acl changes are rejected while inherited' — and the 'and/or' phrasing signals that either or both field groups may be supplied. But it never says when to use this over update_entity_permissions or set_queue_access, leaving sibling selection to inference.

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