Register Worker

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

Annotations already declare destructiveHint=false, idempotentHint=false and readOnlyHint=false. The description adds genuinely useful failure-mode context - the optional tunnel-manager dependency is never needed to import, and affected operations refuse with a named, cause-preserving error rather than raising ImportError - but that context is about recheck/dispatch, not about registration's own behavior (e.g. whether re-registering a host replaces or errors). No contradiction with annotations.

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?

The description is backtick-heavy implementation prose about package composition, RMDD ticket numbers and import semantics - none of which helps an agent invoke the tool. It front-loads package internals ahead of any statement of purpose, and the sentences do not earn their place for a caller.

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 35-parameter tool with zero required parameters and an output schema present, the description should explain which parameters matter for a registration call and how registration relates to the sibling operations. It instead omits the tool's own semantics entirely, leaving the multiplexed parameter surface undirected beyond the schema tags.

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% and every one of the 35 parameters carries its own 'For <op>:' annotation, so the schema already does the routing work. The description adds nothing about parameters, and in particular never clarifies that the 0-required-parameter surface is conditionally required per operation. Baseline 3 applies when the schema carries the load.

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 opening line 'Register worker (rm_remote_workers)' essentially restates the name and title, and the follow-on 'Remote worker registry, immutable source staging, and artifact transport' describes the package as a whole rather than what registering a worker does. Nothing distinguishes this tool from rm_remote_workers_recheck, rm_remote_workers_stage_source, or the other seven siblings in its family.

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?

There is no when-to-use guidance, no alternative named, and no statement of what preconditions registration requires. The only conditional behavior discussed (tunnel-manager absence, host_loss_reconcile always refusing) applies to sibling operations, never to register_worker itself.

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