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

Beyond the readOnly/openWorld annotations, it discloses that checks are deterministic, fetch public pages only, use no AI model and need no account, and that errors come back as one plain sentence. It also names exactly what is recorded (domain and path, never query string or IP) and that the report URL is kept for 30 days, which is real operational context an agent cannot infer.

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?

The purpose and scope lead, followed by output shape, exclusions and data handling in a logical order. It is dense and some clauses run together (the NAP/result sentence is long), but almost every sentence carries information an agent would otherwise lack.

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?

There is no output schema, so the description carries the return contract itself: summary, reportUrl with retention, and the full result structure including null semantics for localSchema. Combined with the error format and recording disclosure, nothing essential for calling or interpreting the tool is missing.

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 100% and the schema already explains that phone and address default to none and are left unchecked, so the description adds little on inputs. Its detail about status values (match, mismatch, not_found, profile_missing) describes outputs rather than parameters, so the baseline 3 holds.

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 names a specific verb and resource set: it checks whether a business page states name, address and phone (NAP consistency) plus LocalBusiness schema, tel links and an embedded map. That is concrete enough to separate it from siblings like check_page or check_agent_readiness without opening either schema.

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 clear usage context ("local SEO questions about a shop, clinic, restaurant or office's website") and explicit exclusions: it does not read the Google Business Profile and does not cover rankings, keyword volumes, backlinks or AI-answer mentions. What's missing is routing to a specific sibling for those excluded cases.

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