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

With no annotations provided, the description carries the full disclosure burden. 'No disk access' is a genuinely useful behavioral fact — it tells the agent the tool will not touch the filesystem, which is the one trait that meaningfully distinguishes it from filesystem-validating alternatives. But it does not disclose what 'safe' means, what the tool returns, or how to interpret the result, leaving significant behavioral gaps for a tool with zero annotation coverage.

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 short sentences with the purpose front-loaded and zero filler — every word earns its place. The structure is exemplary, but the brevity is so extreme relative to the tool's 9-parameter, no-output-schema complexity that it edges into under-specification. A 4 rather than 5 because the economy costs essential detail.

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?

Given nine parameters, 28 siblings, no annotations, and no output schema, the two-sentence description is far from complete. It never states the return shape, the definition of 'safe', or which schema parameters actually apply, and it leaves the massive schema/description mismatch unexplained. An agent cannot reliably know how to invoke this tool correctly from this definition.

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?

Parameter descriptions are self-explanatory and achieve 100% coverage, which would normally warrant a baseline of 3. But eight of the nine parameters describe behavior foreign to a path-safety check (city weather hints, IANA zones, RSS feeds, JSON validation, Git refs), and the description does nothing to reconcile or disambiguate them. An agent could plausibly pass a URL or timezone and get arbitrary behavior, so the description adds no parameter-level value.

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 — 'Check whether a path looks safe' — and adds a clear scope constraint ('No disk access'). It is distinguishable from URL-oriented siblings like browser-url-ok or normalize-url by its focus on file paths. However, the 9-parameter schema is dominated by unrelated operations (weather hints, timezones, RSS feeds, JSON validation), which muddies what the tool actually does despite the clean phrasing.

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?

The description gives no explicit when-to-use or when-not-to-use guidance and names no alternatives. 'No disk access' implies a lightweight shape check, but with 28 siblings including wiki-title-ok and browser-url-ok, an agent gets no help routing to this tool versus a sibling. The implied use case is too thin to count as real guidance.

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