create_note

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

With no annotations at all, the description carries the full burden. It does disclose the most important traits: creation is non-destructive ('never overwrites'), the domain must already exist, body is markdown with pre-heading text allowed, and working notes are excluded from the index. It omits failure behavior (what happens if the target path exists), any permission/auth expectations, and whether index entries are written automatically for project notes.

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 tight sentences, front-loaded with the core action and the never-overwrites guarantee before the variant rules. Dense but no filler; the parenthetical clarifications each carry information. Slightly compressed to the point where the variant rules take a second read.

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 nine-parameter write tool with no annotations and no output schema, the description covers the most consequential semantics but leaves real holes: the path format for a non-working note, the effect on any existing index entry, and the roles of tags and task_id. It is adequate to call the tool but not complete enough to call it confidently in edge cases.

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 0%, so the description must compensate and it only partly does. It explains body (markdown, text before first heading allowed), summary (its index line), and the three header fields decision_status/impl_status/evidence, plus implies the path shape via the working-note layout. It says nothing about title, tags, or task_id, leaving three of nine parameters with no meaning beyond their names.

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 gives a specific verb+resource ('Create a new note') plus a key qualifier ('never overwrites') and a scoping constraint ('in an existing domain'). It clearly distinguishes note creation from sibling create_domain by anchoring on an existing domain, though it never names any sibling explicitly.

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 does give concrete conditional rules for two note variants: a project note needs a summary and page header fields, a working note needs neither and stays out of the index. That is real usage steering. However, it never says when to use create_note versus editing siblings like patch_section, patch_header, or log_append, nor what to do if the note already exists.

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