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

Annotations already declare the tool read-only and idempotent, so the description's job is to add behavioral detail. It does this by specifying the exact fields returned (installed MCPs, connection status, accounts, catalog tool counts). While it does not dive into potential caveats like response size or caching, the provided detail goes meaningfully beyond the annotations and gives the agent a realistic picture of what to expect.

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 description is one compact sentence that front-loads the core action and then lists the four concrete return aspects separated by commas. It is concise without being terse, and every word adds meaning. There is no redundancy or fluff.

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?

Given the tool's simplicity—no parameters, no output schema, and a read-only nature already annotated—the description covers every essential aspect an agent needs. It details the return content thoroughly enough to set expectations and does not omit any crucial behavioral aspect. The description is complete for its intended context.

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?

The input schema is an empty object with 100% schema description coverage (vacuously), and there are zero parameters. The description does not waste characters on params, which is appropriate. Per calibration, zero-parameter tools earn a baseline of 4, and the description adds value by detailing the output instead of the (nonexistent) inputs.

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 begins with a specific verb, 'Returns,' and clearly identifies the resource as 'the current toolkit state.' It enumerates exactly what that state includes: installed MCPs, their connection status, associated accounts, and catalog tool counts. This fully differentiates it from sibling tools like show_version or connect, which address different concerns.

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 description implies when to use the tool—whenever an agent needs a status overview—but it never explicitly states this or contrasts it with alternatives. There is no mention of sibling tools or conditions like 'Use this before connecting' or 'For version details, see show_version.' It provides a clear purpose but leaves the 'when vs. when not' to be inferred.

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