Read remote-spy captures

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

Goes well beyond the read-only/idempotent annotations: it discloses the non-loading read semantics, that Cobalt returns RakNet/actor metadata while Ketamine only captures request arguments, that 'gap' reports expired history, that IDs are scoped to engine and generation, and the required context (active-client, resolved-target). It even directs the agent to tool-schema on failure.

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: the read scope and filter/direction routing come first, and the observe/cost/requires metadata is terse. The full signature restatement duplicates the input schema and the 'Safety: read-only' line duplicates the annotations, which is mild redundancy for a definition this dense.

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 12-parameter read tool with no output schema, it covers return shape qualitatively ('bounded-event-snapshot', per-engine result differences) and the gap/expiry behavior. Missing only explicit pagination rules for the leader result and a clear statement of what happens when no engine is running, so it is close to complete but not exhaustive.

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 baseline is 3. The description mostly restates the signature block that already exists in the schema; its only added semantic value is the afterId cursor scoping ('IDs are scoped to the engine and generation') and the RakNet/engine behavior split, which the schema does not convey.

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 ('Reads bounded captures') and immediately scopes it ('from the selected engine without loading it'). It also differentiates from the adjacent configure-remote-spy (persistent filters) and clear-remote-spy-logs, so an agent can place it among 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 says query filters affect this read only and routes persistent filtering to configure-remote-spy. It also gives engine-level guidance ('Only one engine runs per client') and per-engine differences, but does not spell out prerequisites such as needing ensure-remote-spy to have run first, so it stops short of full when/when-not coverage.

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