read_notes

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial beyond-schema behavior: revision is an update counter with no retained history, views differ in what they omit, full returns a Chinese Markdown guide, and query is literal and capped at 80 characters. This is genuine added context, though pagination and scoping rules are stated in dense fragments rather than cleanly.

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 a run-on wall of semicolon-separated clauses with a confusing opening sentence that spends space on environment chatter rather than the tool's function. Key facts are present but not front-loaded or organized, hurting scannability.

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?

Given an output schema exists, return-value detail is less critical, yet the description still specifies per-view outputs and omits fields appropriately. Combined with the parameter and behavioral coverage for a 6-param, 0%-coverage schema, an agent has enough to call it correctly, though the muddled purpose statement leaves a small 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?

With 0% schema description coverage across 6 parameters, the description carries the full burden and largely succeeds: it explains kind (experience vs TEST), view modes, query length/format, offset continuation ('continue with next_offset'), note_ids semantics (omitted = all, [] = none), and revision meaning. Some fields remain under-specified (exact accepted view/kind strings are not enumerated).

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 tool clearly reads notes/experience topics and the description implies a read operation, but the opening ('Actually read disk, local experience over read-only baseline; TEST is separate') is cryptic and never states plainly what read_notes does. It never names its write counterpart write_note, so differentiation from siblings is left to inference.

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?

Offers concrete sequencing guidance ('Read EXP-GENERAL-GUIDE first, then relevant topics') and disambiguates views (index = previews only, strategy = actionable rules, content/full = audit). It stops short of an explicit when-not-to-use or a direct pointer to a sibling, so it lands below the top tier.

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