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

Goes well past the readOnly/idempotent/non-destructive annotations: it discloses where labels come from (the server's own annotations, otherwise a name-based guess biased toward the more serious kind), that they were not verified by calling the tools, that they do not imply safety, that tool descriptions are excluded, and what an untracked server returns. This is exactly the provenance and confidence context annotations cannot carry.

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-loads the purpose, then spends its length on provenance and limits, every clause carrying signal. The parenthetical glosses on each kind are dense but justified, though the middle paragraph runs long as a single block.

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?

With an output schema present, return shape needn't be explained, and the description still covers the two things an agent genuinely needs: what the labels mean and how much to trust them, plus the not-covered case. Nothing essential to correct invocation is missing.

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%, so the baseline is 3, but the description defines each enum value semantically (money = move or spend, destructive = irreversible changes, send = messages/publication, write = create or change, read = labelled as reading only), which adds meaning beyond the bare enum list and shapes how the kind filter is chosen.

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?

Opens with a specific verb and resource ('Gives the tool names on one tracked vendor MCP server') plus the grouping dimension. That is clearly distinct from find_tool (search) and list_tracked_servers (enumerate servers), so an agent can route without opening a schema.

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?

Establishes the context clearly: one server at a time, optional kind filter, and the 'not covered' outcome for untracked servers implicitly points at list_tracked_servers. It never explicitly names a sibling or states when to prefer find_tool, so the routing is inferred rather than spelled out.

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