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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the marginal bar is met by genuinely new traits: no cost (no quota consumed) and no data exposure, plus a concrete sketch of what is returned for failing tests. Missing only whether results are cached or size-limited.

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-loaded with the core action, followed by return semantics and the when-to-use cue; every sentence carries content. The telegraphic "Costs nothing and sees no data" phrasing is dense but earns its place as behavioral context.

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 and annotations covering the safety profile, the description supplies the remaining needed context: scope, engine fidelity, cost/data stance, and invocation timing. Sufficient for an agent to select and call it correctly without opening the schema.

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 the schema already documents rules, tests, and knownLists. The description adds only light corroboration ("lookups find the test document's items"), not new syntax or format detail, 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?

The description states a specific verb and resource: compile a list's write rules with the API's own engine and run their tests. The scope (a rules-tests-v1 document, diagnostics with line/column, per-test outcomes) clearly separates it from eval_write_rule and validate_sync_document, though no sibling is named by name.

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?

"Use it before saving rules" gives an explicit timing/context for invocation, and "costs nothing and sees no data" clarifies its safe pre-check role. It stops short of naming the alternative tool (e.g. eval_write_rule) for single-rule checks or stating when-not to use it.

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