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

Annotations include readOnlyHint=true, so the safety profile is established. The description adds value by disclosing that certain fields (headingOutline, targetKeywords, contentAnalysis) are conditional on the page being asset-mapped. This is beyond the annotations and helps set expectations for what an agent will receive. However, it doesn't disclose other potential behaviors like error cases or pagination, but given it's a read operation with conditional content, 4 is appropriate. No contradiction with annotations.

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 description is two sentences, concise and front-loaded with the main purpose. The conditional detail is placed after the core returns. It could arguably be split into three parts, but it's efficient. Loses a point because it could be structured with a hint about the conditional fields in a separate clause or list, but it's still well-organized.

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 read-only, 2-parameter tool with no output schema, the description covers the most important context: what it returns, and the condition under which certain fields appear. It doesn't explain nuances like dummy UUIDs (the pattern allows zero and all-f's) or what happens if the page isn't found, but those are minor. Given the tool's simplicity, the description is nearly complete. The conditional field population is the main gap, and it's addressed.

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%, meaning the description adds no parameter-level meaning. The schema itself provides names (pageId, projectId) and UUID formats but no semantic hints. The description mentions that certain fields populate for owned pages but doesn't explain what pageId or projectId refer to beyond common sense. Since there are only 2 simple parameters and the description doesn't explicitly clarify them, but they are fairly self-evident, a baseline 3 is appropriate. It doesn't actively mislead, just isn't helpful.

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 clear verb ('Get') and specific resource ('page dossier') and enumerates what it returns: URL, title, project rankings, ownership. It also clarifies that some fields populate only for owned pages, which distinguishes it from generic page lookup tools. This clearly differentiates it from siblings like list_pages or get_project_asset.

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?

The description implies usage: when you need a comprehensive dossier for a specific page, including ownership and optional analysis fields. It doesn't explicitly state when not to use it or name alternatives, but the richness of the returned fields suggests it is for deeper context rather than listing or asset retrieval. The condition about owned pages is a clear usage hint, though not explicit about alternatives. This is slightly below a 5 due to lack of explicit when-not guidance.

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