List retained clone/newclosure handles

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

Annotations already declare readOnly/idempotent/non-destructive/non-open-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the result is bounded (limit budget), phase=observe, cost=medium, it requires an active client session, and it emits 'bounded-candidates'. It does not describe the exact shape of returned expressions or how the registry is truncated, but it is well above annotation-only coverage.

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 purpose first, then compact labelled facets (Phase/Cost/Requires/Capabilities/Produces/Safety) that are easy to scan. The final 'On failure' sentence is near-boilerplate filler, but overall the text is tight and each label carries information.

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?

There is no output schema, so the description must carry return-value burden; it does state the tool returns reusable expressions plus function metadata and flags bounded output. It also names the precondition (active-client) and cost. Missing only finer detail on result shape and truncation behaviour for a tool with a large sibling surface.

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 both parameters are documented in the schema with types, defaults and min/max bounds. The description only restates the signature, and its 'limit: any?' is looser than the schema's integer 1..200 default 100, so it adds no meaning beyond structured data. 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: reads the bounded getgenv().__mcp_closure_refs registry and returns reusable expressions plus function metadata. It also names the sibling tools that populate that registry (clone-function/new-c-closure/new-l-closure), which helps an agent place it among the many closure/gc siblings. The prose is dense executor jargon, but an agent can tell what it returns.

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?

Usage is only implied, via provenance ('registry created by clone-function/new-c-closure/new-l-closure') and the 'Requires: active-client' constraint. There is no explicit when-not guidance and no alternative tool is named (e.g. get-closure-protos or list-gc-functions for other retrieval paths). The 'On failure: inspect tool-schema' line is a fallback, not routing guidance.

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