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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds genuinely new behavior — that RemoteLock syncs the code down to the physical lock(s) after the call — which tells the agent about an asynchronous side effect on hardware. It stops short of saying what happens on partial sync failure or when access already exists.

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-loaded with the write marker and the core effect, then optional parameters, then the endpoint — a sensible ordering with no wasted clauses. The guest-hours distinction is repeated from the schema, which is minor redundancy.

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 6-parameter mutation with full schema coverage and annotations, the description covers purpose, side effect, and parameter distinctions adequately. The main omissions are return/response expectations and error behavior on duplicate grants, which are small given no output schema exists.

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% and the schema descriptions already explain guest_start_time/guest_end_time as time-of-day overrides and access_schedule_id as recurring hours. The description restates this almost verbatim, adding little beyond what the schema provides, so the baseline 3 applies.

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 (gives access), the resource (lock, door group, location), and the observable effect (PIN/card opens it). The 'WRITE:' prefix and the endpoint line make it immediately distinguishable from read siblings and from remotelock_revoke_access.

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?

The grant scenario is clear and the schedule-vs-guest-window choice is explained, but there is no statement of prerequisites (the access_person_id must already exist — see create_access_user/create_access_guest) and no explicit pointer to revoke_access as the inverse. Usage is implied rather than routed.

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