Monitor one remote

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses that start WRITES LIVE GAME STATE, that a different engine start silently stops the previous spy on this client, that shared capture continues after stop, that no extra hooks are installed, that explicit-mutation-approval is required, and that it mutates persistent executor-side observer state. This is unusually rich disclosure that matches, and does not contradict, the 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 most consequential fact, 'WRITES LIVE GAME STATE on start', is front-loaded first, followed by operational modes and then metadata. The signature, phase, requires/produces, and safety lines are formulaic density but each carries usable information, so it is efficient without being wasteful.

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?

With no output schema and a complex mutating tool, the description supplies preconditions, mutation scope, idempotency character (contextual-write), a verification path (assert-state), and failure remediation (inspect tool-schema). It stops short of describing the shape of fetched captures, but otherwise covers what an agent needs to call it correctly.

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 all six parameters (including enum values, defaults, and the engine-exclusivity note) are already documented in the schema. The description's signature block largely restates those types and enums rather than adding new semantics, so the baseline of 3 is appropriate.

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 states a specific verb+resource set: it starts an engine, opens a view for one remote instance, and exposes start/fetch/stop operations on a remote spy. An agent can tell it monitors a single remote, but it never names or contrasts against close siblings such as remote-spy, trace-remote-traffic, or ensure-remote-spy, so sibling differentiation is left to inference.

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 delineates the three action modes (start writes live state, fetch reads retained captures since the view started, stop closes the view) and lists preconditions (active-client, resolved-target, explicit-mutation-approval). However, it gives no explicit when-to-use-this-vs-alternative guidance against the many other remote-spy and traffic-tracing tools.

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