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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond them: language resolution ('A slug with both languages returns English unless language or a /zh/ URL asks for Chinese'), guaranteed canonicalUrl/author fields, and the domain caveat that digitalgarden.si is an interactive 3D garden rather than a wiki.

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?

Six short sentences, front-loaded with the core action and return shape, then inputs, then edge cases. The citation instruction and the 3D-garden caveat are slightly tangential but each carries weight; nothing is padded.

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?

A two-parameter read tool with full schema coverage and an output schema has little that must be said, and the description covers inputs, language edge cases, and citing rules. The paragraph restating return fields (canonicalUrl, author) is redundant given the output schema but does not leave any observable gap.

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 100%, so baseline would be 3, but the description earns above that by clarifying that slug_or_url accepts a full digitalgarden.si URL and by describing how the language parameter interacts with slug form and /zh/ URLs — meaningful behavior the enum description alone ('zh and zh-CN both mean Chinese') does not convey.

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 and resource: 'Return one note as markdown, plus its canonical URL and author.' Combined with 'Pass a slug or a digitalgarden.si note URL,' an agent knows exactly what this does, and the singular 'one note' implicitly separates it from the list/search siblings. However, no sibling is named, so it does not meet the 5 bar of explicit sibling differentiation.

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 explains how to call it (slug vs URL, language behavior) but never says when to choose get_article over search_articles, list_recent_articles, or list_topics. 'Cite the canonical URL when quoting' is an output-handling instruction, not tool-selection guidance, so no when/when-not or alternative routing is provided.

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