List registry objects

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Safety: read-only' and 'idempotency=read-only' mostly repeat structured data. The description does add genuinely new context — cost=medium and the active-client prerequisite — but 'Produces: bounded-candidates' is too vague to count as real behavioral disclosure.

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?

Purpose is front-loaded and the metadata clauses are compact and information-dense rather than padded. The trailing 'On failure: inspect tool-schema...' sentence is boilerplate that would apply to nearly any tool, but it does not bloat the description.

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 read-only, one-optional-param observe tool with annotations covering the safety profile, this is close to complete: it names the API, the phase, the prerequisite, and the cost. The only gap is that 'bounded-candidates' does not really tell the agent what shape the summarized output takes, and no output schema exists to fill that in.

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 single optional parameter is fully documented in the schema ('omit it to use the server default'). The description only restates the signature '{ threadContext: number? }', adding no meaning beyond the schema, 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 and resource — 'Inspect debug.getregistry() and summarize object types' — naming the exact underlying API and the goal (runtime reversing). It is distinguishable from GC-focused siblings like list-gc-tables or list-global-env-keys, though it never explicitly contrasts itself with them.

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?

'Phase: observe' plus 'Requires: active-client' gives a situational frame and a prerequisite, which is more than nothing. However, there is no when-not guidance and no mention of which sibling to use instead when the agent wants GC tables, threads, or globals rather than the registry.

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