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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by disclosing exactly what state is surfaced (which MCPs, their statuses, connected accounts, tool counts), going beyond the annotation booleans. Slight knock for not covering edge behavior (e.g., what happens with zero MCPs), but strong for an info tool.

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?

One sentence, front-loaded with the verb "Returns", with a scannable colon-enumerated list of the state facets. Every word earns its place — zero fluff with good information density.

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 zero-parameter, read-only inspection tool with strong annotations and no output schema, the description covers all essentials: the resource, the four enumerated state facets, and nothing extraneous. Consistent with the get_calls calibration for complete simple tools.

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?

Zero parameters, so the description has nothing to clarify there. The schema covers 100% of parameters vacuously, and the description appropriately spends no words on nonexistent parameters. Baseline 4 for zero-param tools 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?

"Returns the current toolkit state" uses a specific verb+resource, and the enumeration of what's included (installed MCPs, connection status, accounts, catalog tool counts) crisply distinguishes it from siblings like connect, authenticate, and show_version. The scope is unambiguous.

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?

The usage is implied through words like "current" and "status" — the agent can infer this is for state inspection rather than mutation — but there's no explicit when-to-use guidance, exclusion criteria, or named alternatives (e.g., using connect for establishing connections). Functional but not explicit.

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