cairn_note

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

With no annotations, the description carries the full burden, and it delivers real behavioral context: writes persist across sessions and models, content should not be truncated, transcripts are excluded, and large artifacts should be stored as files with a path reference. It doesn't disclose what a write returns, whether duplicates are deduplicated, or how soon a note becomes searchable, which leaves a gap for a mutation tool.

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?

Four short sentences, front-loaded with purpose before the usage list and the two capture constraints. Each sentence adds information; a small amount of redundancy between "write the complete salient fact" and "without truncating" keeps it from a 5.

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?

No output schema and no annotations exist to offload anything, and the description never says what a successful call produces or how the note becomes retrievable. It also leaves the `tags` parameter entirely unaddressed, so an agent can call it but not fully exploit it.

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%, so the description must compensate. It gives strong guidance for `text` (complete, untruncated, no transcripts) and implicitly maps `kind` via its list of note categories, but `tags` is never mentioned and no parameter is named or typed. Partial compensation only.

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 opens with a concrete verb and resource ("Write a memory to the vault") and frames the scope as ambient capture of durable facts. Every sibling tool (cairn_fetch/search/read/recent/logs) is a read path, so the write-vs-read distinction is unmistakable without needing to name a 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?

It enumerates the triggering cases clearly (decisions, insights, ideas, open items, warnings, procedures discovered while working) and adds a negative rule ("do not paste transcripts — turns are captured separately"). What's missing is an explicit pointer to any alternative tool for the cases this doesn't cover, so it stays below a 5.

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