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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuinely useful behavior beyond that: the hash field is an optimistic-concurrency token consumed by save-global-js as expectedHash, and a contract doc governs first use. Output schema carries the return shape, so no further transparency is needed.

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?

Two compact sentences plus a one-line rule, all front-loaded: what it reads, what it returns, the sequencing constraint, and the doc prerequisite. 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 values are documented elsewhere; listing js/exists/bytes/url/hash in the description is mild duplication. Everything an agent needs to call and sequence the tool is present, and the contract doc pointer covers deeper contract details.

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?

Zero parameters, so the baseline is 4. The description goes slightly further by explaining the downstream meaning of the `hash` output value, though it does not (and need not) describe input syntax.

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 and resource (read the site-wide global.js) and enumerates the returned fields (js, exists, bytes, url, hash). It is clearly distinguishable from its write sibling save-global-js and from get-global-css without opening either 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?

Explicit ordering guidance: read this before save-global-js and pass `hash` back there as expectedHash, plus a prerequisite to read the global-js-contract skill doc before the first call. It stops short of naming an explicit 'when-not' case, but for a zero-param getter the routing is unambiguous.

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