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

Beyond the annotations (readOnlyHint/openWorldHint), the description adds real behavioral context: access checks on 'source ownership, version, expiry and membership', plus an explicit warning that results come from a bounded sample rather than the full site. This tells the agent to expect validated but partial evidence, which annotations alone would not convey.

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 with the resource up front, but several clauses are opaque boilerplate ('Returns typed source evidence and missing-field diagnostics') that consumes space without clarifying action or inputs. The coverage caveat is the only sentence that clearly earns its place.

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 five-parameter, two-required tool with no output schema and zero schema coverage, the description should explain the required identifiers and the similarity threshold. It instead spends its length on provenance boilerplate, so an agent knows the sampling limits but not how to drive the tool 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% and the description documents none of the five parameters. Critical semantics such as what pageUrl represents, what similarity (0-10) thresholds on, and what task_id scopes are entirely absent, leaving the agent to guess from bare field names and min/max bounds.

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 caveat ('bounded crawl sample'), but never gives a clear verb for the core action – it is ambiguous whether it detects duplicate pages, retrieves the content of duplicated pages, or summarizes crawl samples. It also does not distinguish itself from the near-identical sibling nexscope_duplicate_page_tags, so an agent must open the schema to tell them apart.

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?

No when-to-use guidance, no prerequisites, and no mention of the close sibling nexscope_duplicate_page_tags. The clause 'This sample does not describe every page of a website' is a coverage caveat, not a usage condition.

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