read_note

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

No annotations are provided, so the description carries the burden. It discloses the return structure (structured JSON with content, bytes returned, total note size, contentHash), the frontmatter behavior (default false for spans), and the compare-and-swap contract via prevHash. This is solid transparent disclosure. It doesn't mention pagination limits or error behavior for nonexistent paths, but the return-format disclosure is strong.

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?

Three sentences, dense with useful information. Front-loads the core purpose, lists span modes, describes the return contract, and closes with workflow guidance. No filler or repetition of schema details.

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 tool with 5 params and 100% schema coverage, the description covers the purpose, span modes, return format/hash contract, and workflow prerequisites. No output schema exists, but the description explicitly enumerates the return fields (content, bytes, total size, contentHash), compensating well. Minor gaps: doesn't address behavior for nonexistent paths or partial match failures on section names.

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 coverage is 100%, so the baseline is 3. The description adds meaningful value: it ties contentHash to edit tools' prevHash parameter (compare-and-swap), explains how spans map to the various params (section/block/lines), and clarifies frontmatter default behavior for spans. This goes beyond the schema's per-parameter descriptions.

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 uses a specific verb+resource ('Read a note or a span of it') and enumerates three distinct access modes (heading section, block reference, line range). It clearly distinguishes from siblings like outline_note (which returns structure) and search (which finds paths). The tool's role as a read operation is unambiguous.

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?

Explicit guidance: 'Use search or outline_note first to find the right path and section names.' This tells the agent the prerequisite workflow and names the alternative tools to use before invoking read_note. It also explains the contentHash's downstream purpose (pass as prevHash to edit tools), providing clear integration context.

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