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

Annotations only say readOnlyHint=false, destructiveHint=true, openWorldHint=false. The description adds real behavior the annotations cannot convey: this is a partial/patch update, it does not take effect immediately but stages a request that the owner approves in a browser with an agent PIN, and the PIN must never be handled in chat. It also explains what each access level actually grants, which is exactly the kind of context a mutation tool needs.

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, each load-bearing, and the scoping statement is front-loaded ahead of patch semantics, the read-tool pointer, and the staging/PIN warning. No filler or restatement of the schema.

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 9-parameter mutation with no output schema, the description covers everything an agent needs: what is configurable, that unspecified parts are preserved, that the effect is deferred to an owner approval step, and the PIN handling constraint. Nothing material is missing.

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 100%, so the baseline is 3, and the description meaningfully exceeds it by defining the enum semantics the schema only lists: write = everything its capabilities allow, read = search and read only, none = hidden, plus the all/only/except interpretation for folders and calendars. It does not touch provider or workspace, but those are self-documenting in the schema.

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?

The description enumerates exactly what the tool configures: an access role's reach into one mailbox, split into access level, folder rules for file tools, and calendar rules. That content makes it naturally distinguishable from the capability/skill siblings. The one weakness is that the operative verb ('set') lives in the title rather than the description, whose first sentence is a noun phrase ('How far an access role's agents may reach...').

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?

Strong operational guidance: 'Give only the parts you want to change; the others stay as they are' establishes patch semantics, and 'list_access_roles shows the current standing' routes the agent to the read counterpart. The staging workflow and the PIN rule are spelled out clearly. It never names a when-not condition or an adjacent write sibling (set_access_role_capability, set_access_role_skill_access), so the alternative-selection guidance is incomplete.

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