run_inspections

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

With readOnlyHint=false and openWorldHint=true already declared, the description adds genuinely useful behavioral context the annotations cannot carry: the 2,000/day and 600/minute per-property quota ceilings that govern whether a call will succeed. The queue ordering (never-inspected first, then stale) further clarifies what actually happens. It stops short of saying the call consumes quota against a shared budget or that results may be partial when the time budget elapses.

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 sentences, front-loaded with the action and mode selection, then the quota constraint. No filler and nothing structurally out of order.

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 an 8-parameter, no-output-schema tool with an open-world flag and real quota cost, the description covers mode selection and rate limits adequately. It omits what the caller gets back from an inspection run (per-URL verdicts, coverage state, errors) and whether a time-budget expiry yields resumable partial results, both of which an agent needs to plan around.

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 coverage is 75%, so the schema already documents `urls`, `top_pages`, `stale_days`, `recrawled_since`, and `time_budget_seconds`. The description usefully explains the queue default ordering that `stale_days` governs, but says nothing about `max_urls`, `concurrency`, or the interaction between the mode-selecting parameters, leaving the remaining gap unfilled.

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 opens with a specific verb and resource ("Inspect URLs now") and enumerates three operating modes: the queue, an explicit URL list, or top pages. That distinguishes it from the single-URL sibling `inspect_url`, but no sibling is named explicitly, so differentiation is inferred rather than stated.

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 three modes imply when to use each (pass `urls` for an explicit list, `top_pages` for top pages, nothing for the queue), which maps loosely onto the parameters. However, there is no guidance on precedence when `urls` and `top_pages` are both supplied, no exclusions, and no pointer to alternatives such as `queue_urls` or `inspect_url` for queuing versus executing.

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