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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is known. The description adds valuable behavioral context: it depends on historical snapshots ('an event exists only because a snapshot from before it exists') and details the types of changes detected. It does not describe the response format, but this is a minor gap given the strong annotation 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?

The description is front-loaded with the punchy 'The rug pull check' and efficiently packs a lot of useful information into a compact paragraph. The trailing 'Free.' is unnecessary filler, and the parenthetical about 'npm i' is slightly verbose, but overall every other sentence contributes meaningful guidance.

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 tool with simple optional parameters and rich annotations, the description is largely complete. It explains purpose, usage, and a key limitation (snapshot dependency). Since there is no output schema, the lack of an explicit return shape (e.g., a list of change events) is a minor gap, but the description still provides enough for an agent to select and invoke the tool.

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 already describes both parameters with 100% coverage: 'days' as a window and 'packages' as npm package names with the note to omit for the whole feed. The description only repeats 'Pass your own dependency list' without adding new syntax or format details. With full schema coverage, the baseline of 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?

The description opens with 'The rug pull check' and explicitly states it 'answers what CHANGED after it was adopted,' listing concrete examples (install script added, ownership swapped, repository removed, unpublished, provenance lost). It directly distinguishes itself from the sibling `mcp_check_server`, which covers current safety, making the purpose unmistakable.

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 contrasts itself with `mcp_check_server` ('answers whether a package is safe TODAY; this answers what CHANGED'), clearly telling the agent when to choose this tool over the alternative. It also instructs users to 'Pass your own dependency list to check it in one call' and mentions the option to omit packages for the ecosystem feed, giving concrete usage context.

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