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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavioral traits beyond that: deterministic output, stable issue IDs, bounded evidence pagination, no credentials, no model invocation, and no charge. These materially help an agent reason about cost and side effects.

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?

Four short sentences, front-loading what the tool does before the constraints. The 'FREE' emphasis and the list of negatives are borderline filler, but overall it is tight and every sentence carries some information.

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 a 10-parameter tool with nested objects, no output schema, and no parameter descriptions, the description is too thin. It never explains the snapshot shape, what previousIssueIds enables (issue diffing), or how coverage/capturedAt affect results, leaving an agent with an incomplete picture of how to call it correctly.

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 0% across 10 parameters, so the description must carry the load and it largely does not. It hints at the summary/evidence distinction and bounded pagination (mapping to detail/limit/offset), but says nothing about pages, siteUrl, pageUrl, coverage, capturedAt, previousIssueIds, or group. Most inputs remain undocumented in both schema and prose.

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: it audits supplied same-site snapshots for technical SEO issues. It also names scope boundaries (deterministic, local-only) that distinguish it from crawl/fetch siblings like web_readable_fetch or web_page_pack. An agent can identify the capability immediately.

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?

It gives a preference rule ('prefer local crawler reports... to keep raw HTML outside model prompts') and states a negative constraint (no remote crawl), which implies when it applies. However, it never names an alternative tool or a concrete when-to-use/when-not-to-use condition relative to the many sibling tools. Guidance is implied rather than explicit.

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