inspect_url

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

Annotations declare readOnlyHint=false and openWorldHint=true, but the description's phrase 'Stored locally' implies a cached read, creating tension about whether the call mutates or merely retrieves state. It also omits quota/cost behavior, which is significant for a live Google URL Inspection call, and says nothing about what happens when no stored result exists.

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?

It is a single compact sentence with no filler, and the core subject (URL Inspection result from Google) is front-loaded. The parenthetical field list is dense but earns its place by conveying the scope of returned data.

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 only three well-documented parameters and no output schema, the definition is minimally sufficient, but it leaves key questions open: whether the result is live or cached, what is returned when nothing is stored, and how it relates to the queue/run_inspections workflow. Annotations cover the safety profile only partially, so the description should carry more behavioral weight than it does.

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 all three parameters (url, site, language) are already documented in the schema, including the accepted property formats. The description adds no parameter-level meaning beyond that, so the baseline of 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 identifies the resource (Google URL Inspection result) and enumerates fields it covers, but never uses a clear action verb — it reads like a resource label rather than stating whether the tool fetches a stored inspection, triggers a live one, or both. It also does not distinguish itself from siblings like diagnose_url, run_inspections, or list_inspected_urls, leaving the agent to guess its precise role.

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?

There is no when-to-use guidance at all: no mention of prerequisites (does the URL need to be queued or previously inspected?), no exclusions, and no routing to alternatives such as queue_urls/run_inspections for new inspections or list_inspected_urls for enumeration. The agent must infer all of this from sibling names alone.

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