create_access_policy

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

Annotations already declare the write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the description only needs to add context — and it does: the precise effect defaulting logic ('deny only when both user ANY and agent ANY are present; otherwise allow'), the returned UUID, and a read-before-update recommendation. It stops short of stating auth requirements or rollback effects.

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?

Four sentences, all load-bearing: purpose first, then behavioral rule, then return/next-step guidance. The middle sentence about effect inference is dense but earns its place because it changes what a correct call looks like.

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?

An output schema exists, so return-value detail is unnecessary, yet the description still names the returned UUID usefully. Combined with annotations and full schema coverage, the definition is essentially complete; only auth/permission expectations for a workspace-scoped write are unstated.

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 the schema already documents all seven parameters and the baseline would be 3. The description nonetheless sharpens the omitted-effect rule and the constraint that allow requires a specific subject, adding meaning beyond the schema's terser 'create effect is inferred' note.

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 ('Create a workspace access policy') and immediately scopes it by subject kinds (users, groups, agents) and target kinds (MCP tools, provider models). An agent can cleanly distinguish this from get/list/update/delete_access_policy siblings without opening a 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 routes the agent to get_access_policy before later updates, tying an alternative tool to a condition. It also clarifies the effect-inference rule that governs correct input, but it gives no explicit 'when not to use' or prerequisites such as required permissions.

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