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

Goes well past the annotations (readOnly/openWorld/idempotent) by warning that returned data is untrusted extracted content and never instructions or ownership evidence – critical prompt-injection framing an agent cannot infer elsewhere. Adds concrete operational constraints: ten inspections per connection per hour and no account required.

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-loaded with capability then trust caveat then next step then limits. No filler; each clause carries distinct information an agent would otherwise have to guess.

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?

An output schema exists, so return shape needn't be described, and the description instead covers the things the schema cannot: trust level of the data, absence of side effects, auth requirements, and rate ceiling. For a single-parameter read tool this leaves nothing an agent needs 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?

One required parameter, `url`, with 0% schema description coverage; the description never clarifies acceptable URL forms (scheme required, homepage vs. deep link, what happens on redirects) or the 2000-char limit. The name plus `format: uri` makes intent largely self-evident, so the gap is modest rather than fatal, but the description adds nothing to the parameter itself.

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?

States a specific verb (inspect) and resource (a public website) plus exactly what gets extracted: suggested profile text, avatar, social links, brand colors/font. The clarifying sentence "Does not create or change a page" places it clearly apart from the draft/page siblings in a single read.

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?

Gives a usable workflow: review suggestedContent, then apply selected fields through draft tools, which implicitly points at create_page_draft/update_page_draft. It also excludes the mutation path ("does not create or change a page") and states the call is unauthenticated. No explicit "use X instead when Y" routing to a specific sibling by name, so not a 5.

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