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

Annotations already declare read-only, idempotent, closed-world behavior, so the description's job is smaller. It adds real value by disclosing that the response is Markdown and that query strings and anchors are ignored, meaning different URL variants map to the same page.

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?

Two clauses, zero filler, and the primary statement of what the tool returns comes first. The URL-form details follow as the immediately relevant qualification.

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?

With no output schema, stating that the result is Markdown is the key missing piece and it is present. Minor gap: no mention of failure behavior for malformed paths or pages outside the /docs and /learn trees.

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% for the single 'url' parameter, so the description carries the full burden and does so: it enumerates the two accepted path prefixes and the two accepted absolute-URL forms, plus the rule that query and anchor are stripped. Nothing about the input is left ambiguous.

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 ('Read'), a specific resource (docs or course page), and the return format (Markdown). This is clearly distinct from the 'search' sibling, which locates pages rather than returning one page's content.

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 accepted input forms ('/docs/...', '/learn/...', or full openplanr.dev URLs) tell an agent exactly what it may pass, and implicitly scope usage to pages in those trees. It stops short of explicitly contrasting with 'search' or stating what to do when a page isn't found.

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