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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds genuinely new context: that the method is 'versioned', what domains it covers, and the 'Not an official standard' caveat, all of which an agent needs to interpret the returned methodology correctly.

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?

A single front-loaded sentence that names the resource first and then lists contents efficiently, with the disclaimer placed last. Dense but every clause earns its place; no filler.

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?

An output schema exists, so return-value structure need not be explained, and for a zero-param read-only reference tool the description covers scope, versioning and the non-official caveat. The only missing element is a routing hint toward the scoring tool this methodology explains.

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 tool takes zero parameters, so parameter semantics are not applicable and the baseline of 4 applies. The description correctly does not invent any input requirements.

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 ('versioned method of the ... Agent Readability Score') and enumerates what it returns (groups, 14 weighted checks, calculation, caps, bands, limits, MCP/WebMCP judging). This clearly distinguishes it from the sibling check_agent_readability, which computes a score rather than documenting how it is computed, though the description never names that sibling explicitly.

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?

Usage is only implied: the agent can infer this is the reference doc to fetch when it needs to explain or justify a readability score. There is no explicit when-to-use or when-not-to-use statement, and no pointer to the related check_agent_readability sibling that produces the score this method describes.

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