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

Annotations already declare readOnlyHint and openWorldHint=false, so the description's added value is the handling detail: catalog metadata (title, prompt, x-*) is set aside and reported rather than rejected. That's genuinely useful beyond structured data, though it doesn't say what the report looks like or how errors are surfaced.

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?

Three tight sentences, front-loaded with the core action, followed by scope details and a call-to-action. No redundancy or 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?

For a read-only validation tool with a fully described two-parameter schema and no output schema, the description covers what is checked and one important nuance (metadata excluded). What remains unstated is the shape of the validation report, which matters since no output schema exists.

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 description coverage is 100%, so both parameters (ruleset, context) are already documented in the schema, including the rationale for the context field. The description adds nothing about parameter format or expectations, so the baseline 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?

States a specific verb (validate/check) and resource (OpenLint/Spectral ruleset), and enumerates the concrete failure classes it catches: invalid JSONPath, unknown functions, undefined aliases. This clearly separates it from siblings like test_ruleset (running rules against documents) or describe_rule.

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?

"BEFORE running or storing it" and "Run this on every ruleset you write" give explicit timing and a default recommendation. It implies the ordering relative to running/testing but never names test_ruleset as the alternative, so the routing guidance is clear but not exhaustive.

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