cairn_logs

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

With no annotations, the description carries the load and does well: it discloses ordering (newest first), that un-embedded nodes are included, the nightly embedding cycle that gates fetch/search visibility, and the effective result cap (max 60 in schema). It stops short of describing the returned row shape or whether any paging beyond limit exists.

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?

Two sentences, front-loaded with the live-tail/ordering claim, then filters and follow-up. Every clause earns its place — no restating of the name and no filler.

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 five-param read tool with no output schema and no annotations, the description supplies the essential mental model (live, unfiltered-by-embedding, newest first) and the escape hatch to cairn_read. Minor gap: nothing about what a returned node row looks like or truncation behavior in the listing itself.

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 schema already documents all five parameters including examples for kind and session prefix. The description only restates the filter dimensions and adds a max_chars tip that actually pertains to the follow-up cairn_read call, so it adds little beyond structured fields.

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+resource: the live tail of the vault, newest-first, covering all node kinds including conversation turns. It explicitly carves out scope against sibling tools (fetch/search can't see un-embedded nodes), so an agent can distinguish it without opening a schema.

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?

Gives a clear when-to-use condition ('this is how you see what just happened') and names fetch/search as the alternatives that fail for un-embedded nodes, plus a follow-up path via cairn_read. It does not address cairn_recent, whose name implies overlapping 'newest nodes' semantics, leaving one sibling comparison to inference.

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