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

Annotations already declare readOnly/idempotent/closed-world, so the bar is lower, and the description adds genuinely useful behavior: the most recent day may be partial and points at snapshot_at for that. It omits any note on limits, latency, or ordering guarantees, but for a simple read this is solid added context.

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 core purpose and the example output is compact and informative. There is mild redundancy between 'Optional argument: days, default 30' and 'With no arguments you get 30 days', which repeats a fact the schema already encodes.

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 no output schema, the inline example output covers the return shape well, and the default/range/partial-day caveat make it callable without further reading. The only loose end is the bare reference to 'snapshot_at', which is not identified as coming from a specific sibling tool such as snapshot_info.

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% and the single 'days' parameter already documents the 1-365 range and default 30, so the description's restatement ('Optional argument: days, default 30. With no arguments you get 30 days') adds nothing new. Only the 'UTC day' and 'back from the snapshot date' framing slightly enriches semantics, matching the baseline 3 for high-coverage schemas.

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+resource+shape: a ready-to-chart series of new MCP servers per UTC day over the last N days, with an inline example of the returned object. The 'per UTC day' series framing cleanly separates it from cumulative siblings like new_servers_count_since and from registry_totals.

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?

Gives a concrete usage scenario ('Show daily new MCP servers over the last two weeks') and states the no-argument behavior (30 days), so an agent knows when this tool fits. It stops short of naming alternatives or when-not to use it, e.g. versus new_servers_count_since for a single total.

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