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

Annotations only declare readOnlyHint=false and openWorldHint=true, and the description adds meaningful context beyond that: it reports “typed source evidence and missing-field diagnostics,” states that source ownership, version, expiry and membership are validated at run time, and warns that the bounded sample does not cover every page of a site. That is genuinely useful behavioral context about preconditions and sampling limits. It stops short of explaining cost, failure modes, or why the tool is non-read-only.

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 compact sentences with no padding, and the scope-plus-sampling-limitation message is front-loaded. The opening fragment is slightly awkward as a sentence but nothing is wasted.

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?

Without an output schema, the description does a decent job sketching the return shape (“typed source evidence and missing-field diagnostics”) and it flags the sampling caveat. However, for a tool gated on a task_id and a tuned similarity parameter, it leaves the core invocation mechanics and the meaning of the sample boundary unexplained.

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 five parameters, so the description carries the full burden and does not meet it. It never mentions task_id, pageUrl, limit, offset, or the important similarity threshold (0–10), leaving the agent to guess what similarity controls and how pagination interacts with the “bounded sample.”

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 the resource (“Duplicate Page Content”) and a scope qualifier (“from a bounded crawl sample”), but it never uses a verb – “Duplicate Page Content” merely restates the title, so it is unclear whether the tool finds, reports, or filters duplicate content. It does not differentiate itself from close siblings such as nexscope_duplicate_page_tags or nexscope_non_indexable_pages, which an agent could easily confuse it with.

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 explicit when-to-use guidance, no prerequisites stated for obtaining a task_id, and no mention of alternative tools for related duplicate/tag analysis. The only usage-adjacent signal is the closing caveat that the sample is not exhaustive, which is a limitation rather than a routing rule.

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